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. 10-RES-JB
    6. 22623
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or movements involving hands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "sh" within words

    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
     Ajax
    -0.63
     Juven
    -0.62
     sax
    -0.61
     Kore
    -0.60
     Leilan
    -0.59
     certific
    -0.58
     QC
    -0.58
    cki
    -0.58
     facts
    -0.58
     Circuit
    -0.57
    POSITIVE LOGITS
    ifts
    1.38
    ifting
    1.32
    apeshifter
    1.29
    orter
    1.27
    uffle
    1.25
    ooting
    1.24
    rimp
    1.24
    ifted
    1.23
    apesh
    1.22
    adows
    1.22
    Activations Density 0.026%

    No Known Activations