© 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 EvalsExportsinterp-engineNEWAPI 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. 2076
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial and political issues

    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
    288
    +0.19
    0.6%
    284
    +0.13
    0.5%
    98
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.23
    526
    +0.13
    -0.01
    326
    +0.13
    0.17
    Negative Logits
     Annotations
    -1.15
    byter
    -1.06
     condem
    -1.02
    SF
    -0.91
    Rated
    -0.90
    ancies
    -0.89
    ADRA
    -0.87
     Supplement
    -0.86
    BU
    -0.85
     Facilities
    -0.85
    POSITIVE LOGITS
    ousel
    1.14
    balls
    1.03
    bowl
    1.00
    hole
    1.00
     tails
    0.98
    pit
    0.98
    pie
    0.97
    isode
    0.97
     wagon
    0.96
     feathers
    0.94
    Activations Density 4.791%

    No Known Activations