© 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. 11-RES-JB
    11. 22658
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lli
    -0.80
     Sheep
    -0.78
    ŃĶ
    -0.75
     cattle
    -0.68
    epend
    -0.67
    eye
    -0.67
    angelo
    -0.67
    ola
    -0.67
    adata
    -0.67
     lighthouse
    -0.66
    POSITIVE LOGITS
    20
    1.57
     20
    1.57
     21
    1.20
     19
    1.18
    21
    1.10
    19
    1.07
    1920
    1.04
     Twenty
    1.01
     twenty
    0.99
     1920
    0.98
    Activations Density 0.181%

    No Known Activations