© 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. 4118
    Prev
    Next
    INDEX
    Explanations

    medical professionals and their qualifications

    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
    258
    +0.11
    0.5%
    430
    +0.11
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.12
    258
    +0.11
    0.11
    232
    +0.10
    0.08
    Negative Logits
     gor
    -0.77
     ponies
    -0.69
     proxies
    -0.65
     prompt
    -0.63
     samples
    -0.62
    obyl
    -0.61
     compilation
    -0.61
    tics
    -0.60
    gency
    -0.60
     vein
    -0.59
    POSITIVE LOGITS
     Pasadena
    0.78
     Emer
    0.76
     Managing
    0.74
    director
    0.73
    hematic
    0.72
    roit
    0.69
    Instruct
    0.68
     LLP
    0.68
    Chair
    0.67
    Found
    0.67
    Activations Density 3.778%

    No Known Activations