Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 12093
    Prev
    Next
    INDEX
    Explanations

    deadlines

    oai_token-act-pair · gpt-3.5-turbo

    references to important deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ector
    -0.88
    ateur
    -0.83
    stown
    -0.80
    quer
    -0.77
    agate
    -0.72
    otto
    -0.72
    port
    -0.71
    oyal
    -0.70
    jac
    -0.70
    ected
    -0.70
    POSITIVE LOGITS
     deadline
    1.15
     deadlines
    1.12
     looms
    0.82
     imposed
    0.82
     schedule
    0.80
     timeframe
    0.79
     expires
    0.79
     looming
    0.79
     expired
    0.78
     clearance
    0.78
    Activations Density 0.047%

    No Known Activations