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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 4290
    Prev
    Next
    INDEX
    Explanations

    terms related to designated groups or committees formed for specific purposes or investigations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of task forces and committees related to investigations or appointed groups

    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
    ulia
    -0.76
    SourceFile
    -0.67
     Advantage
    -0.64
     Chains
    -0.63
    icio
    -0.63
    bucks
    -0.61
    othe
    -0.60
     Incarn
    -0.60
    Bott
    -0.59
    ãĤª
    -0.59
    POSITIVE LOGITS
     convened
    1.31
     chaired
    1.20
     disbanded
    1.05
     tasked
    1.04
     appointed
    1.03
     investigating
    1.03
    chairs
    0.99
     chairman
    0.94
     headed
    0.94
     members
    0.94
    Activations Density 0.177%

    No Known Activations