© 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. 6429
    Prev
    Next
    INDEX
    Explanations

    years mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly ages and significant metrics associated with events or individuals

    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
     administr
    -0.73
    ebin
    -0.69
     temptation
    -0.68
     suscept
    -0.62
     affair
    -0.61
     subsistence
    -0.60
     incl
    -0.59
     agre
    -0.59
     handle
    -0.59
     tendency
    -0.59
    POSITIVE LOGITS
    th
    1.04
    pc
    0.92
    pb
    0.91
    nm
    0.90
    yo
    0.88
    chan
    0.86
    %-
    0.85
     consecutive
    0.84
    %
    0.84
    Chan
    0.83
    Activations Density 0.258%

    No Known Activations