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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 2522
    Prev
    Next
    INDEX
    Explanations

    numbers, measurements, and units of weight

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heast
    -0.77
    lished
    -0.74
     of
    -0.73
    Of
    -0.68
    of
    -0.66
    cellence
    -0.66
     OF
    -0.64
     Of
    -0.64
    Downloadha
    -0.63
    oft
    -0.61
    POSITIVE LOGITS
    seless
    0.59
     attRot
    0.58
     unden
    0.54
    ãĥĵ
    0.51
    omo
    0.50
     opio
    0.49
     freak
    0.48
     timetable
    0.48
     cream
    0.47
     principle
    0.46
    Activations Density 0.812%

    No Known Activations