© 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. 10-RES-JB
    11. 16362
    Prev
    Next
    INDEX
    Explanations

    events or series of events ordered by time or sequence, similar to a timeline

    oai_token-act-pair · gpt-3.5-turbo

    references to chronological events or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shed
    -0.65
     loopholes
    -0.64
    Magikarp
    -0.63
     Mand
    -0.61
     Mayweather
    -0.61
    WT
    -0.60
     pitch
    -0.60
    holders
    -0.58
     loophole
    -0.58
    holder
    -0.57
    POSITIVE LOGITS
    icle
    1.45
    icles
    1.44
    ograph
    1.43
    ologically
    1.33
    ometer
    1.32
    ology
    1.30
    ographs
    1.29
    ological
    1.22
    otype
    1.20
    ometers
    1.19
    Activations Density 0.035%

    No Known Activations