© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 24568
    Prev
    Next
    INDEX
    Explanations

    mentions of handing something out or over

    oai_token-act-pair · gpt-3.5-turbo

    references to distributions or allocations of resources or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NL
    -0.73
    Stage
    -0.69
    KA
    -0.65
     Featured
    -0.64
    uct
    -0.64
    factor
    -0.64
     Lowell
    -0.61
     Letters
    -0.61
    æĢ
    -0.60
     Phi
    -0.60
    POSITIVE LOGITS
    veland
    0.73
    isans
    0.71
    stretched
    0.71
     supervisors
    0.71
    eger
    0.69
     steering
    0.67
     necks
    0.66
    ioch
    0.66
    esome
    0.66
    ographed
    0.63
    Activations Density 0.127%

    No Known Activations