© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    information related to schedules and locations, especially routes and weeks dates

    oai_token-act-pair · gpt-3.5-turbo

    time-related information, specifically dates and schedules

    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
     respons
    -0.46
    agar
    -0.45
     mitigating
    -0.45
    eni
    -0.43
     meaning
    -0.43
     footing
    -0.43
     customary
    -0.42
     snowball
    -0.42
     Everyday
    -0.41
     privileged
    -0.41
    POSITIVE LOGITS
    etc
    0.72
     etc
    0.66
     ..............
    0.64
    ?????-?????-
    0.62
    OTAL
    0.62
    Ü
    0.60
     ...
    0.56
    ãħĭ
    0.55
     [+]
    0.54
    Appearances
    0.54
    Activations Density 0.472%

    No Known Activations