© 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. 45974
    Prev
    Next
    INDEX
    Explanations

    technical terms related to building and property development

    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
    442
    +0.11
    0.5%
    180
    +0.10
    0.4%
    301
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.07
    442
    +0.10
    0.08
    275
    +0.10
    0.04
    Negative Logits
    undai
    -0.76
    omaly
    -0.74
     hostages
    -0.73
     tremend
    -0.72
     boredom
    -0.72
     motives
    -0.71
    ¿½
    -0.70
     Responsibility
    -0.70
     anonymity
    -0.69
    ĺħ
    -0.69
    POSITIVE LOGITS
    akeru
    0.93
    inki
    0.90
    achus
    0.84
    ettle
    0.80
    erella
    0.78
    vec
    0.78
    oplan
    0.78
    qt
    0.77
    abo
    0.74
    obl
    0.74
    Activations Density 10.681%

    No Known Activations