© 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. 21828
    Prev
    Next
    INDEX
    Explanations

    percentage changes in numerical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and percentages related to trends

    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
    hid
    -0.67
    earable
    -0.63
    £ı
    -0.62
     suffice
    -0.62
     Lack
    -0.60
    kid
    -0.57
    anka
    -0.57
    folk
    -0.56
    avascript
    -0.56
     inexper
    -0.56
    POSITIVE LOGITS
    fold
    1.14
    %;
    1.13
    %,
    1.09
    %.
    1.09
     percent
    1.06
    percent
    1.01
    %
    0.99
     fold
    0.95
    %"
    0.94
     dB
    0.94
    Activations Density 0.101%

    No Known Activations