© 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
    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. 3369
    Prev
    Next
    INDEX
    Explanations

    email-related content

    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 cluster on right - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.19
    0.6%
    172
    +0.14
    0.5%
    499
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.19
    0.08
    311
    +0.14
    0.03
    172
    +0.14
    0.07
    Negative Logits
    alpha
    -1.11
     acquitted
    -1.10
    finished
    -1.07
    sett
    -1.02
    FTWARE
    -1.01
    biased
    -1.00
    found
    -0.98
    clean
    -0.94
    SO
    -0.93
    ratulations
    -0.93
    POSITIVE LOGITS
     least
    1.46
     dusk
    1.34
     halftime
    1.31
    onement
    1.27
    las
    1.23
    hens
    1.22
     variance
    1.20
     midnight
    1.17
     sunset
    1.07
     www
    1.06
    Activations Density 0.799%

    No Known Activations