© 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. 2888
    Prev
    Next
    INDEX
    Explanations

    the names of people or places

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

    proper nouns, particularly names of individuals and places

    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
    atives
    -0.73
    lass
    -0.71
    rament
    -0.68
    ature
    -0.65
    ansk
    -0.61
    many
    -0.60
    bil
    -0.57
    orian
    -0.57
    pan
    -0.57
    ón
    -0.53
    POSITIVE LOGITS
    fen
    0.71
    fields
    0.69
    field
    0.67
    adder
    0.64
    Ĥ¬
    0.63
     Rahman
    0.61
    FFER
    0.59
    ico
    0.59
    CHO
    0.58
    aghan
    0.58
    Activations Density 0.229%

    No Known Activations