© 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. 12-RES-JB
    11. 3012
    Prev
    Next
    INDEX
    Explanations

    words related to news articles or publication information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to media and publishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rants
    -0.93
    amination
    -0.81
    mins
    -0.80
    gins
    -0.78
    any
    -0.77
    an
    -0.73
    eny
    -0.72
    igan
    -0.72
    gen
    -0.72
    orney
    -0.71
    POSITIVE LOGITS
    Editor
    0.85
    E
    0.81
    EB
    0.79
    OTS
    0.72
    Es
    0.71
    BOOK
    0.71
    IV
    0.67
    EED
    0.67
    OTE
    0.67
    DAQ
    0.66
    Activations Density 0.338%

    No Known Activations