© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13703
    Prev
    Next
    INDEX
    Explanations

    phrases related to trust and decision-making

    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
    280
    +0.02
    0.5%
    315
    +0.02
    0.4%
    544
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.02
    0.20
    490
    +0.02
    0.12
    383
    +0.02
    0.14
    Negative Logits
     bil
    -0.15
     saturation
    -0.14
     presentations
    -0.14
     flo
    -0.14
     malaria
    -0.14
    hor
    -0.13
     pulmonary
    -0.13
     redundancy
    -0.13
     urgency
    -0.13
     integration
    -0.13
    POSITIVE LOGITS
    eenth
    0.18
    icent
    0.17
    ij士
    0.16
    liest
    0.16
    abouts
    0.16
    @@@@
    0.15
    .–
    0.14
     Wrest
    0.14
    orce
    0.14
    borgh
    0.14
    Activations Density 11.554%

    No Known Activations