© 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. 40737
    Prev
    Next
    INDEX
    Explanations

    personal interactions and dialogues between characters, potentially focusing on emotional moments

    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
    +0.18
    0.7%
    393
    +0.17
    0.7%
    762
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.18
    0.14
    762
    +0.17
    0.17
    354
    +0.15
    0.12
    Negative Logits
    ĺħ
    -0.92
    ¿½
    -0.89
    GMT
    -0.85
    enges
    -0.84
    ģ«
    -0.80
    eca
    -0.79
    entimes
    -0.78
    ĸļ
    -0.78
    berra
    -0.78
    Ĥª
    -0.78
    POSITIVE LOGITS
    're
    1.62
     guys
    1.52
    've
    1.28
    'll
    1.23
     yourselves
    1.21
    tub
    1.14
    'd
    1.08
     filthy
    1.04
    RS
    0.98
    kai
    0.96
    Activations Density 7.528%

    No Known Activations