© 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. 8-RES-JB
    11. 20416
    Prev
    Next
    INDEX
    Explanations

    keywords related to technical or medical procedures

    oai_token-act-pair · gpt-3.5-turbo

    identifiers and specific acronyms associated with a serious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fires on tokens when the next token starts with a p

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •EggList

    No Comments

    Negative Logits
    ALD
    -0.82
     Haku
    -0.79
    ahl
    -0.75
    alys
    -0.74
    ĭ
    -0.71
    в
    -0.71
    ãĤ¤
    -0.71
    EY
    -0.70
    ald
    -0.70
    egal
    -0.70
    POSITIVE LOGITS
    p
    1.27
    Ps
    1.10
    ps
    1.08
    P
    1.07
    pa
    1.03
    pg
    1.02
    pe
    1.01
    pu
    1.01
    PP
    1.01
     Pon
    1.01
    Activations Density 0.312%

    No Known Activations