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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23232
    Prev
    Next
    INDEX
    Explanations

    the word "squirrel" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "squ."

    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
    geist
    -0.67
     reconciliation
    -0.64
    urally
    -0.62
    wcs
    -0.61
     shrouded
    -0.60
    ------------------------------------------------
    -0.60
     Earth
    -0.60
     earth
    -0.59
     Franz
    -0.58
    ï¸ı
    -0.58
    POSITIVE LOGITS
    irrel
    1.33
    irts
    1.30
    irting
    1.29
    ishy
    1.19
    atters
    1.18
    ishable
    1.18
    irted
    1.14
    atted
    1.11
    ashed
    1.10
    irt
    1.09
    Activations Density 0.017%

    No Known Activations