© 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. 7-RES-JB
    11. 13476
    Prev
    Next
    INDEX
    Explanations

    contractions with an apostrophe followed by the verb "to be"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the contraction "that's."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ievers
    -0.71
    sters
    -0.68
    erers
    -0.67
    ieves
    -0.66
    riors
    -0.64
    nesses
    -0.64
    ling
    -0.63
    icip
    -0.62
    prov
    -0.61
    dylib
    -0.59
    POSITIVE LOGITS
     gonna
    1.08
     gotta
    1.06
     been
    0.76
    SPONSORED
    0.72
     basically
    0.71
     got
    0.70
     alright
    0.70
     Mahjong
    0.70
     why
    0.70
    otta
    0.69
    Activations Density 0.051%

    No Known Activations