© 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. 2770
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons such as "much higher" or "weaker plan."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "much" indicating a significant degree of change or magnitude

    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
     Tags
    -0.80
    ysc
    -0.73
     Releases
    -0.70
     Walls
    -0.65
    querade
    -0.65
    mson
    -0.65
    imester
    -0.64
    anamo
    -0.64
    ensing
    -0.63
    psons
    -0.63
    POSITIVE LOGITS
     simpler
    1.19
     larger
    1.19
     nicer
    1.19
     bigger
    1.15
     smaller
    1.15
     clearer
    1.14
     wider
    1.12
     stronger
    1.12
     narrower
    1.12
     stricter
    1.11
    Activations Density 0.041%

    No Known Activations