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. 11484
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical interaction involving hands

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of obtaining or accessing something physically or metaphorically

    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
    theless
    -0.72
     Supports
    -0.60
    eties
    -0.57
    vertisements
    -0.57
    1920
    -0.55
    adding
    -0.54
    xtap
    -0.53
    ghazi
    -0.52
    due
    -0.52
     suicides
    -0.51
    POSITIVE LOGITS
     dirty
    0.75
    tin
    0.72
     bitten
    0.65
    ultural
    0.63
    ãĤ¶
    0.63
    ½
    0.63
    bit
    0.62
    milo
    0.61
    iotic
    0.61
    prints
    0.60
    Activations Density 0.077%

    No Known Activations