© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13494
    Prev
    Next
    INDEX
    Explanations

    dates and deadlines mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otto
    -0.91
    ector
    -0.85
    omer
    -0.81
    oles
    -0.80
    agate
    -0.74
    our
    -0.73
    ec
    -0.73
    oyal
    -0.71
    ucle
    -0.71
    arel
    -0.71
    POSITIVE LOGITS
     deadlines
    1.29
     deadline
    1.22
     timer
    0.93
     Deadline
    0.89
     timeframe
    0.80
     date
    0.79
     dates
    0.78
     crunch
    0.76
     schedule
    0.76
     mosqu
    0.75
    Activations Density 0.013%

    No Known Activations