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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45995
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or references to people or places

    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
    467
    +0.10
    0.5%
    4
    +0.08
    0.4%
    400
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.12
    41
    +0.08
    0.10
    406
    +0.08
    0.11
    Negative Logits
     Qiao
    -0.68
     Duterte
    -0.65
    Versions
    -0.63
     Paddock
    -0.56
    ivably
    -0.55
    ufact
    -0.54
    ctuary
    -0.52
     Kissinger
    -0.52
    ashtra
    -0.52
    0000000000000000
    -0.51
    POSITIVE LOGITS
    ikuman
    0.78
    lyak
    0.74
    nik
    0.73
    insky
    0.73
    inski
    0.72
    oha
    0.72
    enei
    0.70
    nis
    0.70
    ewski
    0.65
    itsch
    0.64
    Activations Density 7.291%

    No Known Activations