© 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. 11-RES-JB
    11. 20571
    Prev
    Next
    INDEX
    Explanations

    phrases related to heat or warmth

    oai_token-act-pair · gpt-3.5-turbo

    references to heat and temperature

    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
     Goff
    -0.75
    lus
    -0.73
     Mandela
    -0.71
    uthor
    -0.66
    ufact
    -0.66
     Lynd
    -0.66
    ournal
    -0.65
     Commando
    -0.64
    VICE
    -0.63
    ledged
    -0.63
    POSITIVE LOGITS
    hens
    1.38
    wave
    1.30
    waves
    1.22
    seekers
    1.19
    stroke
    1.12
     exch
    1.09
    hen
    0.98
     exhaustion
    0.94
    seeking
    0.93
     waves
    0.93
    Activations Density 0.050%

    No Known Activations