© 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 Local
    9. 6-RES_SCL-AJT
    11. 4160
    Prev
    Next
    INDEX
    Explanations

    references to political campaigns, staffing, and strategies

    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
    +0.23
    1.2%
    432
    +0.10
    0.6%
    655
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    618
    +0.23
    0.15
    679
    +0.10
    0.20
    673
    +0.09
    0.10
    Negative Logits
    Redd
    -0.60
     Grade
    -0.59
     Hig
    -0.57
     Pillar
    -0.55
    OME
    -0.54
     HIP
    -0.53
     Hier
    -0.53
     Cald
    -0.53
    ENGTH
    -0.51
     Kinder
    -0.51
    POSITIVE LOGITS
     allege
    0.70
    chair
    0.68
    mates
    0.67
     denies
    0.66
     disav
    0.66
     accuse
    0.66
     insist
    0.64
     deny
    0.62
     reacted
    0.60
     seized
    0.60
    Activations Density 10.785%

    No Known Activations