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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24277
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a decision or action

    oai_token-act-pair · gpt-3.5-turbo

    actions indicating decision-making and participation in political or formal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellent
    -0.75
    not
    -0.74
    albeit
    -0.72
    terness
    -0.71
     fortunately
    -0.70
    byte
    -0.69
    arently
    -0.68
    stellar
    -0.67
     luckily
    -0.67
    loo
    -0.66
    POSITIVE LOGITS
     anymore
    1.63
     any
    1.45
     nor
    1.43
     anything
    1.32
     anyone
    1.15
     ANY
    1.09
     anybody
    1.09
     unless
    0.96
     anywhere
    0.94
     anytime
    0.91
    Activations Density 0.390%

    No Known Activations