© 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 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. 21761
    Prev
    Next
    INDEX
    Explanations

    comparisons to other entities

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons between different entities or categories

    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
    steen
    -0.70
    ãĥĻ
    -0.63
    aily
    -0.59
    itone
    -0.58
    angan
    -0.57
    attribute
    -0.57
    =#
    -0.56
    hower
    -0.56
    rang
    -0.55
    instein
    -0.55
    POSITIVE LOGITS
     surveyed
    0.81
     except
    0.80
     besides
    0.79
     vying
    0.73
     nationwide
    0.73
     whatsoever
    0.71
    .'
    0.71
     due
    0.67
    '.
    0.67
     combined
    0.67
    Activations Density 0.235%

    No Known Activations