© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 32624
    Prev
    Next
    INDEX
    Explanations

    references related to the concept of independence, including terms like "independence," "Constitution," "Declaration of Internet Freedom," and "Memorial Day."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.12
    0.8%
    339
    +0.09
    0.6%
    254
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.12
    0.30
    138
    +0.09
    0.28
    64
    +0.08
    -0.20
    Negative Logits
    venants
    -0.59
    ester
    -0.58
    abol
    -0.57
    geon
    -0.57
    vana
    -0.53
    edo
    -0.53
    esthetic
    -0.52
    rations
    -0.52
    ying
    -0.52
    esters
    -0.52
    POSITIVE LOGITS
     Day
    0.66
     Independence
    0.60
     Month
    0.59
    stad
    0.54
    sburg
    0.54
     Fathers
    0.52
     Lights
    0.51
     Films
    0.51
     Partnership
    0.51
     Strikes
    0.51
    Activations Density 9.055%

    No Known Activations