© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 17724
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of places and people

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and brands associated with various fields or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bers
    -0.73
     APPLIC
    -0.71
     instr
    -0.69
     ÂŃ
    -0.64
     Discipline
    -0.63
     Instr
    -0.63
     pat
    -0.59
     inst
    -0.58
     palp
    -0.58
     Administ
    -0.58
    POSITIVE LOGITS
    ctuary
    0.84
    ËĪ
    0.82
    iverpool
    0.80
    sterdam
    0.79
    itone
    0.78
    ilingual
    0.78
    utenberg
    0.77
    luaj
    0.76
    itcher
    0.75
    onut
    0.75
    Activations Density 0.283%

    No Known Activations