© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1062
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    significant negative events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.74
    ½
    -0.71
    adra
    -0.71
    awei
    -0.71
    ternity
    -0.70
    boro
    -0.69
     Saiyan
    -0.68
    heit
    -0.68
    zona
    -0.68
    ī
    -0.67
    POSITIVE LOGITS
    Scroll
    0.77
    However
    0.73
    READ
    0.71
    PHOTOS
    0.70
    Asked
    0.70
    Tickets
    0.68
    Yesterday
    0.68
    Pict
    0.68
    HM
    0.68
    Officers
    0.67
    Activations Density 0.233%

    No Known Activations