© 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. 33891
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers or counts

    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
    157
    +0.11
    0.6%
    497
    +0.08
    0.5%
    303
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    739
    +0.11
    0.03
    418
    +0.08
    0.08
    345
    +0.08
    0.06
    Negative Logits
    quartered
    -0.65
    hetical
    -0.64
     Guilty
    -0.55
    qua
    -0.55
    mur
    -0.48
     voic
    -0.48
    venge
    -0.47
    uras
    -0.47
     deceased
    -0.46
     harmed
    -0.46
    POSITIVE LOGITS
     waivers
    0.59
    rocal
    0.58
    ernels
    0.57
     weeds
    0.55
    idden
    0.55
    abouts
    0.54
    =~=~
    0.54
     midday
    0.53
    akuya
    0.53
    anism
    0.53
    Activations Density 6.259%

    No Known Activations