© 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. 14198
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons indicating quantity

    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
    447
    +0.15
    0.9%
    655
    +0.12
    0.7%
    214
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.28
    362
    +0.12
    0.18
    385
    +0.08
    0.20
    Negative Logits
    ç·
    -0.60
    EMENT
    -0.59
    Interstitial
    -0.57
    microsoft
    -0.55
    owe
    -0.55
    DH
    -0.54
    ALE
    -0.53
    ALSE
    -0.53
    ilic
    -0.52
    oris
    -0.52
    POSITIVE LOGITS
    whelming
    0.58
     doubling
    0.54
     200
    0.51
     8000
    0.51
    etheless
    0.50
    race
    0.50
     7000
    0.49
     400
    0.48
    lihood
    0.47
     seventy
    0.47
    Activations Density 9.275%

    No Known Activations