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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5501
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names related to politics and events such as Clinton, Trump, and specific individuals and organizations associated with them

    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
    65
    +0.15
    0.5%
    288
    +0.13
    0.5%
    398
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.18
    65
    +0.13
    0.11
    542
    +0.12
    0.10
    Negative Logits
    hemy
    -1.04
    terday
    -0.97
    NetMessage
    -0.96
    rss
    -0.94
     ..........
    -0.91
    htaking
    -0.88
    uria
    -0.88
    utm
    -0.88
    itars
    -0.87
    olen
    -0.83
    POSITIVE LOGITS
     version
    1.19
     universe
    1.14
     fanbase
    1.12
     lineup
    1.10
     electorate
    1.09
     playbook
    1.09
     equivalent
    1.07
     Pirates
    1.07
     Revolution
    1.04
     logo
    1.00
    Activations Density 2.460%

    No Known Activations