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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3699
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology services

    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
    288
    +0.28
    1.0%
    712
    +0.16
    0.6%
    61
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.07
    712
    +0.16
    0.05
    682
    +0.13
    0.06
    Negative Logits
    uran
    -1.09
    sty
    -0.97
    lr
    -0.92
    Filename
    -0.88
    vu
    -0.86
    nih
    -0.84
    kered
    -0.84
    osta
    -0.83
    iary
    -0.83
    ean
    -0.82
    POSITIVE LOGITS
     provider
    1.42
     Provider
    1.41
     providers
    1.37
     Provided
    1.17
     rendered
    1.13
     Employees
    1.02
     acad
    0.99
     outage
    0.99
    VICE
    0.97
    oteric
    0.95
    Activations Density 0.808%

    No Known Activations