© 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. 12278
    Prev
    Next
    INDEX
    Explanations

    names or titles, likely related to political figures or events

    oai_token-act-pair · gpt-3.5-turbo

    identifiers and numerical data

    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
     fung
    -0.77
     Gaw
    -0.74
     Locke
    -0.73
     Greenwood
    -0.71
     ESC
    -0.70
     Gree
    -0.70
     Gaia
    -0.67
    Cu
    -0.67
     Gre
    -0.66
     Cu
    -0.66
    POSITIVE LOGITS
    42
    1.47
    45
    1.43
    44
    1.40
    46
    1.38
    41
    1.37
     42
    1.36
    43
    1.36
     44
    1.35
     45
    1.35
     43
    1.32
    Activations Density 0.109%

    No Known Activations