© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14400
    Prev
    Next
    INDEX
    Explanations

    references to people involved in legislative or political activities and legal 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
    •Layer 6 UMAP region: Mostly-local cluster on left - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.24
    0.9%
    608
    +0.13
    0.5%
    362
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.24
    0.06
    692
    +0.13
    0.06
    109
    +0.13
    0.07
    Negative Logits
    uality
    -1.05
    ppa
    -1.04
    bia
    -0.93
    aser
    -0.93
    itta
    -0.90
    ashtra
    -0.90
    claimer
    -0.89
    imir
    -0.88
    ndum
    -0.85
    bard
    -0.85
    POSITIVE LOGITS
     virtue
    1.56
    laws
    1.15
    products
    1.09
    product
    0.98
     means
    0.98
    gone
    0.97
     multiplying
    0.96
    catch
    0.93
     statute
    0.89
     leaps
    0.85
    Activations Density 0.928%

    No Known Activations