© 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. 8-RES-JB
    11. 3262
    Prev
    Next
    INDEX
    Explanations

    words related to dog breeds

    oai_token-act-pair · gpt-3.5-turbo

    words related to dog breeds and their characteristics

    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
    inki
    -0.83
    ashtra
    -0.67
     mafia
    -0.65
     Whitman
    -0.59
    imaru
    -0.58
     thunder
    -0.58
    isSpecialOrderable
    -0.58
    esar
    -0.57
     Confederation
    -0.56
    biz
    -0.55
    POSITIVE LOGITS
    dden
    0.98
    tein
    0.80
    owship
    0.72
    ©¶æ
    0.72
    ense
    0.71
     Pradesh
    0.71
    antage
    0.70
    eval
    0.69
    fman
    0.67
    lete
    0.66
    Activations Density 0.134%

    No Known Activations