© 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. 4-RES-JB
    11. 10187
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format (month-day-year)

    oai_token-act-pair · gpt-3.5-turbo

    date and time formats

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

    No Comments

    Negative Logits
     accus
    -0.76
    lain
    -0.69
    izon
    -0.68
    CLUD
    -0.65
    anova
    -0.64
    INO
    -0.63
    ANT
    -0.62
    obar
    -0.61
    antry
    -0.61
    ople
    -0.61
    POSITIVE LOGITS
    å¹
    0.83
    released
    0.67
    01
    0.67
     onwards
    0.67
    release
    0.67
    02
    0.66
    election
    0.65
     edition
    0.65
    etheus
    0.63
    20439
    0.63
    Activations Density 0.156%

    No Known Activations