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. 7-RES-JB
    6. 20082
    Prev
    Next
    INDEX
    Explanations

    mentions of legislation or policy actions

    oai_token-act-pair · gpt-3.5-turbo

    currency-related terms

    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
     navig
    -0.68
     trainer
    -0.68
     mathemat
    -0.67
     saddle
    -0.63
     Seym
    -0.63
     encl
    -0.62
     managed
    -0.60
     exploited
    -0.60
     ridden
    -0.59
     Tasman
    -0.59
    POSITIVE LOGITS
    onto
    1.11
    their
    1.00
    there
    0.96
    them
    0.92
    him
    0.91
    rough
    0.89
    selves
    0.88
    his
    0.86
    different
    0.84
    against
    0.84
    Activations Density 0.294%

    No Known Activations