© 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. 18591
    Prev
    Next
    INDEX
    Explanations

    photographs or images

    oai_token-act-pair · gpt-3.5-turbo

    mentions of images and visual content

    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
    xtap
    -0.77
    aunder
    -0.66
    owicz
    -0.63
    cles
    -0.63
     immersion
    -0.62
     interven
    -0.61
     antit
    -0.61
     incorpor
    -0.61
     compost
    -0.60
     plots
    -0.59
    POSITIVE LOGITS
    everal
    0.80
    ampa
    0.76
    LOS
    0.75
    DEN
    0.73
    ccording
    0.71
    Madison
    0.71
    Jer
    0.71
    ALT
    0.70
    NFL
    0.69
    heastern
    0.69
    Activations Density 0.082%

    No Known Activations