© 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. 8-RES-JB
    11. 5074
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to quantities and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wiser
    -0.61
     brunt
    -0.61
     EVEN
    -0.61
     safer
    -0.60
     whiff
    -0.59
     grate
    -0.59
     regress
    -0.58
     recess
    -0.56
     sag
    -0.56
    etsk
    -0.56
    POSITIVE LOGITS
    %.
    0.84
     apiece
    0.84
    +.
    0.79
    hz
    0.76
    %,
    0.74
    +,
    0.72
    20439
    0.69
    Hz
    0.68
    votes
    0.68
     magnitude
    0.67
    Activations Density 0.246%

    No Known Activations