© 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. 2702
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "character"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ch."

    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
    PORT
    -0.88
    WARD
    -0.82
    DragonMagazine
    -0.78
    ITED
    -0.77
    gaard
    -0.75
    ENCE
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.74
    INGTON
    -0.73
    berman
    -0.73
    glas
    -0.69
    POSITIVE LOGITS
    amps
    1.26
    icago
    1.13
    inese
    1.05
    ipper
    1.03
    isel
    1.03
    umps
    1.02
    umb
    1.01
    amber
    1.01
    ippers
    1.01
    okers
    1.00
    Activations Density 0.012%

    No Known Activations