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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24525
    Prev
    Next
    INDEX
    Explanations

    locations where events or incidents occurred

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or times in events

    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
    FTWARE
    -0.85
    Lens
    -0.73
    alpha
    -0.73
    gravity
    -0.69
    ratulations
    -0.69
    Pac
    -0.69
    Russ
    -0.68
    biased
    -0.68
    REDACTED
    -0.68
    aceutical
    -0.67
    POSITIVE LOGITS
     least
    1.19
     halftime
    1.05
    onement
    0.99
    rial
    0.93
     midday
    0.93
     dusk
    0.90
    abase
    0.86
    hens
    0.85
     noon
    0.82
     midnight
    0.81
    Activations Density 0.268%

    No Known Activations