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. 19094
    Prev
    Next
    INDEX
    Explanations

    references to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in relation to quantities or states of being

    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
    fulness
    -0.72
    iliation
    -0.72
    eness
    -0.71
    gypt
    -0.70
    matter
    -0.68
    ename
    -0.67
    illation
    -0.66
    rix
    -0.64
    itude
    -0.62
     Featured
    -0.62
    POSITIVE LOGITS
     indications
    1.22
     signs
    0.97
     discrepancies
    0.95
     exceptions
    0.94
     fewer
    0.94
     conflicting
    0.94
     rumours
    0.94
     fears
    0.93
     rumors
    0.93
     similarities
    0.92
    Activations Density 0.064%

    No Known Activations