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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45864
    Prev
    Next
    INDEX
    Explanations

    information related to political and social movements, including protests, campaigns, and legislative battles

    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
    447
    +0.29
    1.4%
    34
    +0.10
    0.5%
    205
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.23
    540
    +0.10
    0.17
    531
    +0.10
    0.09
    Negative Logits
    undai
    -0.67
     Seym
    -0.64
    Instruct
    -0.63
     certific
    -0.62
    uddenly
    -0.60
     Birthday
    -0.60
    mson
    -0.58
    aturdays
    -0.57
    Fac
    -0.57
     Converted
    -0.56
    POSITIVE LOGITS
     against
    0.79
    Enlarge
    0.76
     waged
    0.76
    ggle
    0.76
     underway
    0.75
    athon
    0.74
    iest
    0.72
    naire
    0.72
    chest
    0.71
    jam
    0.71
    Activations Density 9.441%

    No Known Activations