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. 15137
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions and processes, such as filtering, painting, cutting, curing, priming, and cleaning

    oai_token-act-pair · gpt-3.5-turbo

    past participles and adjectives in a technical or procedural context

    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
    eeks
    -0.74
    stadt
    -0.70
    Found
    -0.67
    onnaissance
    -0.62
    èĥ
    -0.61
    Org
    -0.61
    involved
    -0.61
    ours
    -0.60
    Capture
    -0.60
    acio
    -0.60
    POSITIVE LOGITS
     separately
    0.97
     differently
    0.96
     by
    0.96
     into
    0.95
     away
    0.92
     properly
    0.85
     beforehand
    0.85
     out
    0.84
     extensively
    0.84
     externally
    0.83
    Activations Density 0.287%

    No Known Activations