© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    political figures and related terms

    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
    650
    +0.16
    0.5%
    560
    +0.14
    0.5%
    136
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.16
    0.05
    744
    +0.14
    0.05
    247
    +0.12
    0.04
    Negative Logits
    Äĩ
    -1.12
    icular
    -1.08
    ettel
    -1.02
    USD
    -0.94
    anco
    -0.93
    gs
    -0.90
    cially
    -0.90
    GF
    -0.90
    iru
    -0.89
    oqu
    -0.88
    POSITIVE LOGITS
    Rog
    0.99
     Settlement
    0.97
     Legions
    0.92
     Orders
    0.89
     agre
    0.89
    asse
    0.87
     Orn
    0.84
     Islanders
    0.83
    Fight
    0.82
     Claims
    0.82
    Activations Density 0.532%

    No Known Activations