Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13581
    Prev
    Next
    INDEX
    Explanations

    financial values and measurements

    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
    316
    +0.13
    0.5%
    100
    +0.13
    0.5%
    153
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.13
    0.07
    316
    +0.13
    0.07
    153
    +0.12
    0.06
    Negative Logits
    iatus
    -0.76
     Pros
    -0.76
     pastoral
    -0.75
     proble
    -0.74
    ↵Âł
    -0.70
    galitarian
    -0.69
    chers
    -0.69
    edIn
    -0.69
     Cong
    -0.68
     Barbie
    -0.67
    POSITIVE LOGITS
    à¤
    0.88
    ा
    0.84
    nesia
    0.83
    Apps
    0.83
    50
    0.82
    assium
    0.81
    oÄŁan
    0.81
    Ability
    0.80
    antine
    0.80
    696
    0.79
    Activations Density 2.603%

    No Known Activations