© 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
    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. 8384
    Prev
    Next
    INDEX
    Explanations

    HTML image elements with specified attributes like width, height, and alt text

    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
    228
    +0.08
    0.5%
    289
    +0.07
    0.4%
    257
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.08
    0.02
    334
    +0.07
    0.02
    176
    +0.07
    0.02
    Negative Logits
     behavi
    -0.54
    BILITIES
    -0.53
    utical
    -0.53
    ÄŁ
    -0.52
     anyways
    -0.50
     Fug
    -0.49
    ãĤ¡
    -0.49
    ctive
    -0.49
    .–
    -0.49
    animous
    -0.48
    POSITIVE LOGITS
    Nav
    0.56
    ilde
    0.55
    und
    0.53
    unda
    0.52
    edin
    0.49
    affer
    0.48
    unct
    0.47
    column
    0.47
    word
    0.46
    ring
    0.45
    Activations Density 0.132%

    No Known Activations