© 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. 8-RES-JB
    11. 17216
    Prev
    Next
    INDEX
    Explanations

    references to fire incidents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fire" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.99
     Vide
    -0.72
     Lans
    -0.71
    DonaldTrump
    -0.68
     Virtue
    -0.68
    edy
    -0.66
    Birth
    -0.66
    atem
    -0.65
     Phar
    -0.64
     Vec
    -0.64
    POSITIVE LOGITS
     exting
    1.20
    storm
    1.13
    fighting
    1.10
    flies
    1.07
    storms
    1.06
    proof
    1.06
    places
    1.02
    brand
    1.01
    fight
    0.99
    balls
    0.98
    Activations Density 0.039%

    No Known Activations