© 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. 11-RES-JB
    11. 2708
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps in the format of month, day, and year

    oai_token-act-pair · gpt-3.5-turbo

    date and time information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attle
    -0.63
    channelAvailability
    -0.63
    acebook
    -0.62
    rss
    -0.62
    uca
    -0.61
    hetically
    -0.61
    AUT
    -0.61
    clips
    -0.60
    ancers
    -0.59
    merce
    -0.59
    POSITIVE LOGITS
     00
    1.33
     05
    1.23
     06
    1.23
     08
    1.22
     07
    1.22
     04
    1.21
     09
    1.20
     02
    1.19
     03
    1.17
     01
    1.14
    Activations Density 0.059%

    No Known Activations