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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 1189
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Bitcoin" at various levels and its related concepts, like blockchain and cryptocurrencies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.22
    0.7%
    26
    +0.15
    0.5%
    290
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.06
    26
    +0.15
    0.05
    723
    +0.15
    0.04
    Negative Logits
     Ake
    -1.07
     pestic
    -1.05
    FU
    -1.03
     Eisenhower
    -1.03
     Pruitt
    -0.91
     Ange
    -0.89
     USAF
    -0.88
    dB
    -0.87
     Afric
    -0.87
    contact
    -0.87
    POSITIVE LOGITS
    ica
    1.14
    bitcoin
    1.11
     millionaires
    1.09
    Talk
    1.05
    Cash
    1.05
    ensis
    1.02
     Core
    1.01
    coins
    0.99
    cius
    0.98
    Coin
    0.98
    Activations Density 0.679%

    No Known Activations