© 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. 12697
    Prev
    Next
    INDEX
    Explanations

    contact information within text for services or products

    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
    575
    +0.16
    0.7%
    377
    +0.15
    0.6%
    415
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.07
    326
    +0.15
    0.06
    575
    +0.14
    0.06
    Negative Logits
    loss
    -0.84
    ²¾
    -0.83
    avin
    -0.77
    oid
    -0.76
    alog
    -0.73
    birth
    -0.72
    omic
    -0.71
    inating
    -0.71
    nesses
    -0.71
    aline
    -0.71
    POSITIVE LOGITS
     suite
    1.19
     Suite
    1.07
     suites
    1.06
    mble
    0.93
    door
    0.77
    cases
    0.76
     reservation
    0.74
    gur
    0.74
    CRIP
    0.73
    artment
    0.72
    Activations Density 0.489%

    No Known Activations