© 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. 2027
    Prev
    Next
    INDEX
    Explanations

    references to layers in a physical and technical context

    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: Mixed in middle - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    216
    +0.15
    0.5%
    99
    +0.14
    0.5%
    98
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.08
    288
    +0.14
    0.10
    99
    +0.14
    0.06
    Negative Logits
    lishing
    -1.16
    ãĥĪ
    -1.06
    vous
    -1.03
    itarian
    -1.02
    ilee
    -0.99
    orie
    -0.99
    inant
    -0.99
    shire
    -0.99
    nia
    -0.97
    BAT
    -0.94
    POSITIVE LOGITS
     layers
    1.65
     thickness
    1.40
     layer
    1.40
    layer
    1.11
     opacity
    1.06
    coat
    1.00
    sheets
    1.00
     veil
    0.99
     conceal
    0.98
    river
    0.98
    Activations Density 1.238%

    No Known Activations