© 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. 9-RES-JB
    11. 23524
    Prev
    Next
    INDEX
    Explanations

    links to shareable content such as news articles and stories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to articles and their dissemination online

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ceilings
    -0.67
    ibles
    -0.62
     beginnings
    -0.61
     salads
    -0.61
    Ĭ±
    -0.61
     chops
    -0.60
     maid
    -0.59
     snacks
    -0.59
     missiles
    -0.58
     impulses
    -0.58
    POSITIVE LOGITS
    ittee
    0.71
    gha
    0.71
    hei
    0.68
    legram
    0.65
    ipient
    0.64
    ocument
    0.62
    eless
    0.61
     TRANS
    0.60
    urrection
    0.60
    stakes
    0.60
    Activations Density 0.092%

    No Known Activations