© 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. 8-RES-JB
    11. 8977
    Prev
    Next
    INDEX
    Explanations

    timestamps with specific dates and times

    oai_token-act-pair · gpt-3.5-turbo

    specific time and date 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
     plots
    -0.69
    uctor
    -0.68
    ²¾
    -0.65
    ulates
    -0.65
    agall
    -0.62
    henko
    -0.62
    ieg
    -0.61
    antis
    -0.61
    semb
    -0.59
     schemes
    -0.59
    POSITIVE LOGITS
    quickShipAvailable
    0.94
     UTC
    0.78
    UTC
    0.75
     GMT
    0.70
    Reviewer
    0.66
     PDT
    0.65
     HOU
    0.64
     PST
    0.64
     Tik
    0.63
     Apply
    0.62
    Activations Density 0.082%

    No Known Activations