© 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. 7581
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental actions 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
    393
    +0.22
    0.7%
    484
    +0.17
    0.6%
    696
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.22
    0.07
    735
    +0.17
    0.05
    616
    +0.14
    0.05
    Negative Logits
    rex
    -1.05
    expensive
    -1.05
    efficient
    -1.04
    raid
    -1.01
    anners
    -0.98
    alus
    -0.95
    comes
    -0.94
    english
    -0.94
    rea
    -0.91
    ades
    -0.91
    POSITIVE LOGITS
    THING
    1.46
     remaining
    1.16
     undue
    1.15
    body
    1.14
     conceivable
    1.13
     lingering
    1.03
     semblance
    1.03
    where
    1.02
     further
    1.00
     imaginable
    0.99
    Activations Density 0.852%

    No Known Activations