© 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. 1-RES-JB
    11. 15320
    Prev
    Next
    INDEX
    Explanations

    words related to ice or cold environments

    oai_token-act-pair · gpt-3.5-turbo

    references to "ice."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bul
    -0.76
    FG
    -0.75
    rompt
    -0.74
    verb
    -0.72
    usc
    -0.70
    hester
    -0.70
    digit
    -0.69
    Priv
    -0.69
    INGTON
    -0.68
    ________________
    -0.67
    POSITIVE LOGITS
     rink
    1.39
     cream
    1.15
     skating
    1.12
     ice
    1.05
     hockey
    0.92
     Ice
    0.92
    breaker
    0.91
    breakers
    0.90
     melt
    0.87
     glacier
    0.87
    Activations Density 0.012%

    No Known Activations