Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 14690
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity named Ald

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or possibly multiple individuals named Aldous

    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
    pmwiki
    -0.93
     tits
    -0.66
     deaf
    -0.64
    vous
    -0.63
     dism
    -0.63
    awaru
    -0.62
     sight
    -0.62
    uberty
    -0.61
    ãĥ¥
    -0.59
    udeau
    -0.59
    POSITIVE LOGITS
    rums
    0.96
    uin
    0.96
    ives
    0.90
    wich
    0.87
    rum
    0.86
    o
    0.85
    yssey
    0.83
    onia
    0.82
    rica
    0.82
    orf
    0.82
    Activations Density 0.035%

    No Known Activations