© 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. 8-RES-JB
    11. 6036
    Prev
    Next
    INDEX
    Explanations

    informational narratives or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to news stories and significant events

    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
    iolet
    -0.73
    inia
    -0.70
    inav
    -0.65
    udget
    -0.62
    abbling
    -0.62
    hire
    -0.60
    imble
    -0.58
    entimes
    -0.58
    ankind
    -0.58
    razil
    -0.57
    POSITIVE LOGITS
    liest
    1.07
    iest
    1.01
    same
    0.90
     anew
    0.88
     himself
    0.86
     correctly
    0.83
     equivalent
    0.80
     anonymously
    0.79
     behind
    0.77
    wrong
    0.76
    Activations Density 0.394%

    No Known Activations