© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 3487
    Prev
    Next
    INDEX
    Explanations

    names of individuals or titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names of political figures and references to political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aido
    -0.79
    idable
    -0.78
    cffffcc
    -0.74
    oses
    -0.71
    tis
    -0.69
    ternity
    -0.69
    itiz
    -0.68
    ions
    -0.68
    andum
    -0.67
    vet
    -0.65
    POSITIVE LOGITS
    ec
    0.62
    128
    0.61
    YN
    0.60
    Ey
    0.60
     Barron
    0.57
     dece
    0.55
    E
    0.55
     gull
    0.55
    ync
    0.55
     Vide
    0.55
    Activations Density 0.204%

    No Known Activations