© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    technical terms or abbreviations related to optimization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Opt" and variations related to optimized performance or products

    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
    nces
    -0.63
    WHERE
    -0.62
    ppo
    -0.61
    SHIP
    -0.58
    ãĥĨãĤ£
    -0.57
     arrest
    -0.56
     Danger
    -0.56
     SDL
    -0.56
    fighting
    -0.54
     Hebdo
    -0.53
    POSITIVE LOGITS
    imum
    1.57
    imal
    1.52
    imus
    1.28
    ima
    1.21
    icians
    1.06
    ometry
    1.06
    imize
    1.05
    ician
    1.02
    imo
    1.02
    ics
    1.01
    Activations Density 0.039%

    No Known Activations