© 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. 7-RES-JB
    11. 23124
    Prev
    Next
    INDEX
    Explanations

    astronomical objects, specifically comets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of comets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skirts
    -0.82
    antha
    -0.80
    uckland
    -0.77
    dos
    -0.75
    otics
    -0.69
    imm
    -0.65
    aceutical
    -0.65
    Hom
    -0.64
    OUT
    -0.64
    lasses
    -0.64
    POSITIVE LOGITS
     Ping
    0.93
     comet
    0.89
     nucleus
    0.75
    hedral
    0.71
     Osiris
    0.70
     Confederation
    0.69
     crust
    0.67
     Chaser
    0.66
     Nost
    0.65
     constellation
    0.64
    Activations Density 0.036%

    No Known Activations