© 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. 10-RES-JB
    11. 9917
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods such as "throughout the day" or "earlier in the week."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oma
    -0.80
    TextColor
    -0.70
    mates
    -0.68
    acons
    -0.66
    BIL
    -0.65
    nit
    -0.64
    interstitial
    -0.63
    imate
    -0.61
    Space
    -0.60
    obar
    -0.60
    POSITIVE LOGITS
     day
    1.18
     year
    1.17
     week
    1.13
     semester
    1.13
     lifespan
    1.11
     duration
    1.10
     process
    1.09
     decade
    1.07
     month
    1.06
     course
    1.05
    Activations Density 0.097%

    No Known Activations