© 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. 11720
    Prev
    Next
    INDEX
    Explanations

    mentions of the season 'winter'

    oai_token-act-pair · gpt-3.5-turbo

    references to winter and its associated characteristics

    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
     Dawkins
    -0.74
    roid
    -0.72
    kick
    -0.70
    zos
    -0.70
    iff
    -0.63
    ront
    -0.63
    plet
    -0.62
     ATK
    -0.59
    uterte
    -0.59
    cells
    -0.59
    POSITIVE LOGITS
     winter
    3.63
     winters
    2.73
    winter
    2.46
    Winter
    2.32
     summer
    2.31
     Winter
    2.20
     autumn
    2.07
     summers
    1.88
     spring
    1.85
     snowy
    1.65
    Activations Density 0.013%

    No Known Activations