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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5893
    Prev
    Next
    INDEX
    Explanations

    timestamps in text

    oai_token-act-pair · gpt-3.5-turbo

    timestamps or time-related information

    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
    izations
    -0.59
     orderly
    -0.56
     behav
    -0.54
     inspectors
    -0.54
     collaborations
    -0.53
     sweater
    -0.53
     cleaner
    -0.53
     Emer
    -0.52
     improvements
    -0.52
     investigations
    -0.52
    POSITIVE LOGITS
     apiece
    1.11
     intervals
    0.83
    point
    0.77
     sidx
    0.75
    uca
    0.73
    fps
    0.72
     onwards
    0.69
     discretion
    0.69
    Hz
    0.68
    cand
    0.68
    Activations Density 0.184%

    No Known Activations