© 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. 7454
    Prev
    Next
    INDEX
    Explanations

    text related to quotes and statements made in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of certain symbols or special characters

    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
    conservancy
    -0.89
    wagen
    -0.82
     ascending
    -0.74
    agate
    -0.73
    userc
    -0.71
     manip
    -0.70
     disguise
    -0.69
    immers
    -0.68
     conver
    -0.68
     coales
    -0.68
    POSITIVE LOGITS
     Ibid
    0.91
    ONSORED
    0.90
    ————
    0.89
    ————————
    0.88
    HAM
    0.78
    ––
    0.77
    =-=-=-=-=-=-=-=-
    0.75
    Jeremy
    0.74
     Timeline
    0.71
    Laughs
    0.70
    Activations Density 0.093%

    No Known Activations