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. 33814
    Prev
    Next
    INDEX
    Explanations

    phrases expressing importance or significance in a broad sense

    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
    +0.30
    1.3%
    679
    +0.11
    0.5%
    213
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.30
    0.41
    447
    +0.11
    0.42
    64
    +0.11
    -0.19
    Negative Logits
    ilk
    -0.81
    terness
    -0.79
    ivable
    -0.78
     Fever
    -0.77
    ibal
    -0.74
    çİĭ
    -0.73
    iverpool
    -0.72
    arthed
    -0.72
    ©¶æ
    -0.72
    Kay
    -0.72
    POSITIVE LOGITS
     distinction
    0.87
     milestone
    0.83
     distingu
    0.81
     ingredient
    0.80
     parts
    0.80
     importance
    0.80
     enough
    0.79
     milestones
    0.78
     portions
    0.78
     hinge
    0.77
    Activations Density 11.270%

    No Known Activations