© 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. 0-RES-JB
    11. 6657
    Prev
    Next
    INDEX
    Explanations

    mentions of the Winter Olympics, particularly the location 'Sochi'

    oai_token-act-pair · gpt-3.5-turbo

    references to the Winter Olympics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FIR
    -0.73
     Hindus
    -0.73
     lakh
    -0.70
    roid
    -0.70
    uterte
    -0.68
    indu
    -0.65
     crore
    -0.63
    tex
    -0.63
     cartridges
    -0.63
    UID
    -0.63
    POSITIVE LOGITS
     Winter
    3.84
    Winter
    3.23
    winter
    2.21
     Summer
    2.12
     winter
    2.05
     Autumn
    1.71
    Summer
    1.71
     Spring
    1.69
     winters
    1.61
     Fall
    1.56
    Activations Density 0.010%

    No Known Activations