© 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. 32776
    Prev
    Next
    INDEX
    Explanations

    indications or signals of various types related to a wide range of topics

    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
    +0.14
    1.2%
    679
    +0.07
    0.7%
    575
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.14
    0.29
    255
    +0.07
    0.16
    393
    +0.06
    0.33
    Negative Logits
    zanne
    -0.38
    nee
    -0.38
    iqueness
    -0.36
    enic
    -0.36
    prus
    -0.36
    pee
    -0.34
    oho
    -0.34
    zik
    -0.33
    iba
    -0.33
    pered
    -0.32
    POSITIVE LOGITS
     indication
    0.45
     hint
    0.45
     indications
    0.44
     signs
    0.43
    orial
    0.41
     thereof
    0.40
     whatsoever
    0.39
     signal
    0.39
     Signs
    0.38
     hints
    0.38
    Activations Density 16.175%

    No Known Activations