© 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
    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. 14545
    Prev
    Next
    INDEX
    Explanations

    political figures and events, including elections, candidates, and government actions

    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
    168
    +0.06
    0.5%
    131
    +0.06
    0.4%
    635
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.06
    0.05
    701
    +0.06
    0.04
    738
    +0.05
    0.03
    Negative Logits
    qt
    -0.45
     bush
    -0.44
    ĸļ
    -0.42
    Wan
    -0.41
    ãĤ£
    -0.40
     crow
    -0.40
    gdala
    -0.39
     Bai
    -0.39
     Budd
    -0.36
    doi
    -0.36
    POSITIVE LOGITS
    ACY
    0.59
    roups
    0.55
    UES
    0.52
    ULAR
    0.49
    END
    0.48
    UE
    0.46
    ENTS
    0.46
    ATE
    0.45
    ATOR
    0.45
    ENCY
    0.45
    Activations Density 0.107%

    No Known Activations