© 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. 10704
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental policies and funding

    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
    +0.34
    1.4%
    0
    +0.15
    0.6%
    128
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.34
    0.14
    393
    +0.15
    0.14
    484
    +0.12
    0.13
    Negative Logits
    hov
    -0.98
    acci
    -0.93
    idia
    -0.89
    ouls
    -0.83
    zza
    -0.81
    osta
    -0.81
    othal
    -0.81
    terness
    -0.79
    nikov
    -0.79
    igmatic
    -0.79
    POSITIVE LOGITS
     hence
    1.20
     consequently
    1.17
     thereby
    1.11
     therefore
    1.09
     thus
    1.08
     thence
    0.95
     consequ
    0.95
     secondly
    0.91
     vice
    0.88
    romeda
    0.85
    Activations Density 1.745%

    No Known Activations