© 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. 6660
    Prev
    Next
    INDEX
    Explanations

    languages based on religion and politics

    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
    +0.33
    1.1%
    385
    +0.16
    0.5%
    362
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.08
    393
    +0.16
    0.09
    553
    +0.16
    0.05
    Negative Logits
    Reviewer
    -1.06
    UC
    -1.02
    Quantity
    -1.02
    REM
    -1.02
    Serv
    -1.01
    TABLE
    -1.01
    Texture
    -1.00
    UNCH
    -1.00
    Required
    -0.99
    VER
    -0.99
    POSITIVE LOGITS
     allies
    1.56
     own
    1.53
     attendant
    1.36
     surroundings
    1.30
     ensuing
    1.27
     defenders
    1.26
     accompanying
    1.25
     friends
    1.23
     affiliates
    1.21
     cohorts
    1.20
    Activations Density 1.546%

    No Known Activations