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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 19851
    Prev
    Next
    INDEX
    Explanations

    mentions of customization or custom-made items

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "custom" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.80
     Kinn
    -0.75
     Abortion
    -0.74
    Õ
    -0.73
    ï¸
    -0.72
    oof
    -0.71
     Dwight
    -0.71
    =-=-=-=-
    -0.71
     CrossRef
    -0.69
     Doe
    -0.69
    POSITIVE LOGITS
     custom
    1.19
    isable
    1.15
    arily
    1.13
     customized
    0.98
     customization
    0.97
    ised
    0.93
     tailor
    0.93
    isations
    0.92
    custom
    0.90
     recre
    0.90
    Activations Density 0.010%

    No Known Activations