© 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. 11-RES-JB
    11. 10028
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, specifically mentioning the time of day (e.g., midday)

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific time frame or period, particularly indicated by "mid" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pains
    -0.65
    edIn
    -0.63
     supervised
    -0.59
     prejudice
    -0.58
    itsch
    -0.57
     bona
    -0.57
     Lieberman
    -0.57
     Bib
    -0.56
     Rubin
    -0.56
     Berk
    -0.56
    POSITIVE LOGITS
    terms
    1.36
    century
    1.28
    season
    1.25
    wives
    1.24
    stream
    1.22
    wife
    1.22
    west
    1.21
    section
    1.21
    winter
    1.20
    western
    1.19
    Activations Density 0.018%

    No Known Activations