© 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. 22604
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to extreme cold or freezing temperatures

    oai_token-act-pair · gpt-3.5-turbo

    references to frozen substances or conditions

    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
    rahim
    -0.82
    lia
    -0.81
    anan
    -0.77
    rious
    -0.76
    uan
    -0.75
    ours
    -0.75
    ###
    -0.75
    istrate
    -0.73
    iliary
    -0.72
    orer
    -0.72
    POSITIVE LOGITS
     yogurt
    1.06
     peas
    0.95
     cust
    0.89
     frozen
    0.85
     desserts
    0.82
     froze
    0.81
    bite
    0.79
     cold
    0.78
     temperatures
    0.78
     rink
    0.78
    Activations Density 0.045%

    No Known Activations