© 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. 13431
    Prev
    Next
    INDEX
    Explanations

    elongated mentions of durations of time, especially involving years

    oai_token-act-pair · gpt-3.5-turbo

    references to the lengths of contracts or agreements in years

    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
     Dispatch
    -0.76
    urnal
    -0.74
     Cosponsors
    -0.68
    anguage
    -0.65
     Panel
    -0.64
    agogue
    -0.63
    aughtered
    -0.63
    isy
    -0.63
     Hearing
    -0.62
     Hamb
    -0.61
    POSITIVE LOGITS
    ichick
    0.80
     undrafted
    0.79
    contract
    0.78
     undefeated
    0.75
     MLB
    0.72
     starters
    0.72
    players
    0.71
    rafted
    0.70
     STATS
    0.70
    NFL
    0.69
    Activations Density 0.075%

    No Known Activations