Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16832
    Prev
    Next
    INDEX
    Explanations

    items tied to a specific physical attribute, specifically those that are slick and smooth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the string "sl"

    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
     pleas
    -0.68
    bell
    -0.64
     directions
    -0.63
     Nam
    -0.62
    IFIC
    -0.62
    lde
    -0.61
     Sons
    -0.58
    wealth
    -0.58
    enegger
    -0.57
     Haas
    -0.57
    POSITIVE LOGITS
    anted
    1.19
    asher
    1.18
    udge
    1.16
    inging
    1.15
    otted
    1.14
    ashes
    1.13
    ugg
    1.13
    umping
    1.10
    ighter
    1.08
    ippery
    1.07
    Activations Density 0.023%

    No Known Activations