© 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. 12091
    Prev
    Next
    INDEX
    Explanations

    people speaking or giving speeches in various settings

    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
    Already
    -0.69
    Need
    -0.66
    Else
    -0.66
    lords
    -0.64
    76561
    -0.63
     nowhere
    -0.63
    Unfortunately
    -0.62
    Sov
    -0.62
    Basically
    -0.62
     Gone
    -0.61
    POSITIVE LOGITS
    window
    0.92
     during
    0.87
     onstage
    0.83
    */(
    0.82
     Attend
    0.77
     gestures
    0.76
    FILE
    0.76
     REUTERS
    0.75
     portraits
    0.73
     celebrate
    0.73
    Activations Density 0.102%

    No Known Activations