© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 16725
    Prev
    Next
    INDEX
    Explanations

    numerical quantities related to time periods or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to quantities and counts

    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
    merce
    -0.76
    abus
    -0.73
    lass
    -0.68
    heter
    -0.68
    shape
    -0.68
    early
    -0.67
    oner
    -0.65
    hower
    -0.64
    andr
    -0.64
    aban
    -0.64
    POSITIVE LOGITS
     vacancies
    0.94
     fewer
    0.90
    acity
    0.83
     tonnes
    0.80
     unanswered
    0.78
     grandchildren
    0.78
     million
    0.77
     openings
    0.77
     degrees
    0.76
     acres
    0.75
    Activations Density 0.205%

    No Known Activations