© 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. 22024
    Prev
    Next
    INDEX
    Explanations

    words related to questioning or pondering

    oai_token-act-pair · gpt-3.5-turbo

    words related to existential or philosophical inquiries

    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
    ħĭ
    -0.84
    ij士
    -0.81
    querque
    -0.77
    INAL
    -0.74
     DEFENSE
    -0.74
    catentry
    -0.73
    Pear
    -0.73
    ibrary
    -0.72
    ãĥ¼ãĥĨ
    -0.72
    Īè
    -0.69
    POSITIVE LOGITS
    nesday
    1.13
    ewater
    0.89
    bledon
    0.81
    risome
    0.77
    ÅĤ
    0.73
    hof
    0.71
    ipeg
    0.71
    itzer
    0.69
     Password
    0.69
    wright
    0.68
    Activations Density 0.067%

    No Known Activations