© 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. 20214
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating measurements

    oai_token-act-pair · gpt-3.5-turbo
    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
    ollah
    -0.75
    apego
    -0.66
    effects
    -0.61
    ependent
    -0.59
     stash
    -0.58
     stink
    -0.58
    ream
    -0.58
     aroma
    -0.56
    eus
    -0.56
     rebirth
    -0.55
    POSITIVE LOGITS
     apiece
    1.29
     per
    0.91
     (~
    0.83
    renheit
    0.83
     squared
    0.80
    /$
    0.79
     ±
    0.77
     versus
    0.77
    +.
    0.76
    /.
    0.75
    Activations Density 0.123%

    No Known Activations