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. 8-RES-JB
    6. 6
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their associations or attributes

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals or figures

    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
    anced
    -0.64
    Notice
    -0.64
    vation
    -0.62
    antics
    -0.61
     suffice
    -0.60
    pection
    -0.60
    iety
    -0.60
    Requ
    -0.60
    Specific
    -0.59
    osc
    -0.59
    POSITIVE LOGITS
     founding
    0.89
     pioneer
    0.86
     famed
    0.84
     renowned
    0.84
     beloved
    0.80
     founder
    0.79
     leader
    0.78
     acclaimed
    0.77
     legendary
    0.76
     guitarist
    0.76
    Activations Density 0.420%

    No Known Activations