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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1714
    Prev
    Next
    INDEX
    Explanations

    phrases related to change in direction or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "turn around."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.81
    ged
    -0.67
     tatt
    -0.67
    chem
    -0.63
    ãĥı
    -0.63
    pee
    -0.62
    accompan
    -0.61
    rought
    -0.61
     cyt
    -0.61
    twitch
    -0.60
    POSITIVE LOGITS
    ruciating
    0.78
    wagen
    0.75
    erous
    0.74
    ernaut
    0.74
    atform
    0.68
    itect
    0.67
    allery
    0.67
    ãħĭ
    0.67
     corners
    0.62
    ivas
    0.62
    Activations Density 0.024%

    No Known Activations