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

    Neuronpedia

    Jacobian LensNEW
    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. 6444
    Prev
    Next
    INDEX
    Explanations

    statements related to political or 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
    393
    +0.24
    0.8%
    720
    +0.20
    0.7%
    332
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.24
    0.09
    546
    +0.20
    0.06
    719
    +0.14
    0.06
    Negative Logits
    ORPG
    -1.18
    adelphia
    -1.11
    icc
    -1.10
    hess
    -1.09
    izon
    -1.03
    nih
    -1.00
    orthy
    -1.00
    asons
    -0.99
    agate
    -0.97
    SourceFile
    -0.96
    POSITIVE LOGITS
     moreover
    1.35
     consequently
    1.34
     secondly
    1.33
     alas
    1.31
     therefore
    1.25
     accordingly
    1.24
     importantly
    1.22
     furthermore
    1.19
     cru
    1.13
     preferably
    1.10
    Activations Density 1.911%

    No Known Activations