© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7745
    Prev
    Next
    INDEX
    Explanations

    references to the name "Frost"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Frost" and related terms referring to cold or frostbite

    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
    ctr
    -0.73
    bay
    -0.70
    \\\\\\\\
    -0.68
     Bin
    -0.66
    wat
    -0.64
     detained
    -0.64
     Santos
    -0.64
    igslist
    -0.63
     Nom
    -0.63
    ambo
    -0.63
    POSITIVE LOGITS
     Frost
    3.75
     frost
    2.76
    rost
    2.48
     Freeze
    1.40
     Frozen
    1.31
     freeze
    1.23
     Glacier
    1.21
     Snow
    1.21
     Ice
    1.21
     snow
    1.12
    Activations Density 0.021%

    No Known Activations