© 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. 6-RES-JB
    11. 17526
    Prev
    Next
    INDEX
    Explanations

    questions being posed in various contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "asked"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Es
    -0.68
    marine
    -0.66
    egg
    -0.66
    scrib
    -0.64
    ãĥĩãĤ£
    -0.64
    Fit
    -0.64
    Blu
    -0.63
    tten
    -0.61
     Dong
    -0.61
    paio
    -0.61
    POSITIVE LOGITS
     quizz
    1.04
     rhet
    0.96
     asked
    0.86
     posed
    0.85
     questioned
    0.79
     athlet
    0.77
     sarcast
    0.76
    ioned
    0.71
     polled
    0.69
     prompts
    0.68
    Activations Density 0.017%

    No Known Activations