© 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. 682
    Prev
    Next
    INDEX
    Explanations

    statements about specific topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    the word "about" in various contexts related to different subjects or themes

    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
    İĭ
    -0.74
    fax
    -0.72
     Peaks
    -0.72
    psons
    -0.67
    oland
    -0.65
    ocaly
    -0.65
    aments
    -0.63
     Writ
    -0.62
    aro
    -0.61
    CHR
    -0.61
    POSITIVE LOGITS
     halfway
    0.76
     calib
    0.68
     decentral
    0.67
     educating
    0.67
     powering
    0.67
    pheus
    0.66
    uble
    0.64
    ingu
    0.63
    roying
    0.62
     repealing
    0.62
    Activations Density 0.049%

    No Known Activations