© 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. 9496
    Prev
    Next
    INDEX
    Explanations

    expressions involving the ability or potential to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "could" indicating potential or ability

    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
     Ing
    -0.72
    furt
    -0.67
    cedented
    -0.64
     vacated
    -0.60
    washer
    -0.59
     honors
    -0.58
     Rising
    -0.58
     honoring
    -0.57
     reven
    -0.57
    holder
    -0.57
    POSITIVE LOGITS
    adian
    1.04
     feas
    1.03
    ĸļ
    0.99
    berra
    0.98
     be
    0.89
     conce
    0.89
     attest
    0.88
     possibly
    0.88
    nt
    0.87
     conclud
    0.86
    Activations Density 0.085%

    No Known Activations