© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    dates and times in a text

    oai_token-act-pair · gpt-3.5-turbo

    time references, particularly phrases indicating the beginning or occurrence of events

    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
    ĺħ
    -0.75
    abled
    -0.68
    soType
    -0.65
    onga
    -0.63
    tions
    -0.63
    oln
    -0.63
    itability
    -0.63
    spread
    -0.63
    sers
    -0.62
     risked
    -0.61
    POSITIVE LOGITS
     earnest
    1.45
     dawn
    0.85
     dusk
    0.79
     kindergarten
    0.76
     January
    0.72
     noon
    0.71
     mids
    0.70
     sunrise
    0.68
     zero
    0.66
     April
    0.65
    Activations Density 0.118%

    No Known Activations