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. 34832
    Prev
    Next
    INDEX
    Explanations

    political and philosophical terms related to socialism, industrialization, economy, and social equality

    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
    622
    +0.22
    0.8%
    132
    +0.14
    0.5%
    670
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.22
    0.22
    213
    +0.14
    0.05
    203
    +0.14
    0.07
    Negative Logits
     Coulter
    -0.98
    ividual
    -0.92
    ãĥ¼ãĥĨãĤ£
    -0.91
     EntityItem
    -0.91
     eminent
    -0.90
     Sons
    -0.87
     CBI
    -0.85
    arians
    -0.83
     DPR
    -0.80
     Catalyst
    -0.78
    POSITIVE LOGITS
    spective
    1.43
    cks
    1.43
    bably
    1.38
    spection
    1.32
    tto
    1.31
    blems
    1.29
    active
    1.28
    dden
    1.27
    phant
    1.26
    intestinal
    1.25
    Activations Density 9.814%

    No Known Activations