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

    Neuronpedia

    Jacobian LensNEW
    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. 33368
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations and military contexts, such as terrain features, warfare actions, and historical events

    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
    701
    +0.15
    0.7%
    678
    +0.11
    0.5%
    421
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.15
    0.14
    232
    +0.11
    0.09
    107
    +0.10
    0.04
    Negative Logits
    staking
    -0.70
    ITED
    -0.68
    GMT
    -0.66
    VICE
    -0.66
     sterling
    -0.66
     affairs
    -0.65
    BIL
    -0.63
     Canaver
    -0.61
    915
    -0.61
    INC
    -0.61
    POSITIVE LOGITS
    ulhu
    1.46
    ttp
    1.38
    orne
    1.27
    umbnail
    1.15
    urst
    1.10
    ieves
    1.07
    ousands
    1.05
    ieving
    1.03
    opter
    1.03
    ousand
    1.02
    Activations Density 10.643%

    No Known Activations