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. 3903
    Prev
    Next
    INDEX
    Explanations

    news and information related to political figures and events

    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
    226
    +0.16
    0.5%
    543
    +0.15
    0.5%
    145
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.16
    0.03
    267
    +0.15
    0.04
    145
    +0.13
    0.03
    Negative Logits
    istry
    -1.29
    istration
    -1.15
    lain
    -1.08
    ģĸ
    -1.02
    ority
    -1.01
    liga
    -1.00
     certs
    -1.00
    bucks
    -0.99
    steam
    -0.97
    yout
    -0.97
    POSITIVE LOGITS
     Juliet
    1.28
     Jacqu
    1.19
     POLITICO
    1.13
     Falk
    1.09
     Investigative
    1.04
     Jonathan
    1.04
     Neal
    1.04
     NPR
    1.04
     Carrie
    1.03
     Intellectual
    1.02
    Activations Density 0.465%

    No Known Activations