© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 39429
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities and historical events

    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
    +0.15
    0.7%
    104
    +0.11
    0.5%
    391
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.15
    -0.21
    535
    +0.11
    0.04
    614
    +0.11
    0.03
    Negative Logits
     presentations
    -0.90
     stunts
    -0.82
     brainstorm
    -0.81
     anecd
    -0.79
    Sym
    -0.79
    ogle
    -0.77
     skew
    -0.76
     prank
    -0.74
     thrill
    -0.74
     performances
    -0.74
    POSITIVE LOGITS
     annexed
    1.36
     territ
    1.15
     sovereignty
    1.14
     territory
    1.13
     annexation
    1.12
     annex
    1.10
     sovereign
    1.09
     territorial
    1.07
     territories
    1.07
     Territ
    1.07
    Activations Density 18.299%

    No Known Activations