© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and references

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to quantities or measurements

    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
    heit
    -0.83
    kees
    -0.80
     contempl
    -0.75
     adolesc
    -0.74
     attent
    -0.69
     favorably
    -0.66
     favor
    -0.66
     undermin
    -0.65
    cho
    -0.65
     retali
    -0.63
    POSITIVE LOGITS
    CBC
    0.95
    READ
    0.88
    hma
    0.84
    Numbers
    0.82
    Ur
    0.79
    Asked
    0.79
     CBC
    0.79
    Lt
    0.77
    Officials
    0.77
    Owner
    0.77
    Activations Density 0.319%

    No Known Activations