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. 9-RES-JB
    6. 21239
    Prev
    Next
    INDEX
    Explanations

    statements about moving away from simplicity towards complexity, especially in the realm of cooking or food preparation

    oai_token-act-pair · gpt-3.5-turbo

    references to systemic issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undo
    -0.65
    yellow
    -0.65
    Nev
    -0.62
    assic
    -0.62
    orange
    -0.60
    Pink
    -0.58
    but
    -0.58
    hex
    -0.58
    Ult
    -0.57
     Furious
    -0.57
    POSITIVE LOGITS
     nonetheless
    1.15
    etheless
    0.88
     oneself
    0.87
     itself
    0.87
     downright
    0.81
     actual
    0.77
     awfully
    0.74
     fundamentally
    0.73
     goddamn
    0.72
     damn
    0.71
    Activations Density 0.985%

    No Known Activations