© 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. 2-RES-JB
    11. 18207
    Prev
    Next
    INDEX
    Explanations

    verbs related to performing actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "perform."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wart
    -0.73
    raft
    -0.71
    shi
    -0.67
     Dish
    -0.64
    mes
    -0.63
    so
    -0.63
    fram
    -0.62
     Lime
    -0.61
     Mole
    -0.61
    conom
    -0.61
    POSITIVE LOGITS
     evaluations
    0.90
     performed
    0.90
     abortions
    0.86
     corrid
    0.82
     performs
    0.82
    OGR
    0.81
    acus
    0.78
    ð
    0.77
    isons
    0.76
    inav
    0.76
    Activations Density 0.014%

    No Known Activations