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

    Neuronpedia

    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. 10-RES-JB
    11. 13771
    Prev
    Next
    INDEX
    Explanations

    words related to guidance or advice

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gu" or its variations, suggesting a focus on guidance or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rings
    -0.65
    ŃĶ
    -0.65
     owl
    -0.64
     womb
    -0.64
    gdala
    -0.63
    hower
    -0.63
    cling
    -0.63
    hawks
    -0.61
    ¿½
    -0.60
     spaced
    -0.59
    POSITIVE LOGITS
    idelines
    1.43
    inea
    1.34
    pta
    1.32
    ilty
    1.30
    errilla
    1.30
    bernatorial
    1.29
    cci
    1.28
    essing
    1.26
    arding
    1.22
    inness
    1.21
    Activations Density 0.019%

    No Known Activations