Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21726
    Prev
    Next
    INDEX
    Explanations

    keywords related to heat or temperature

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to temperature and heating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VICE
    -0.75
     Mandela
    -0.71
    vous
    -0.70
    RB
    -0.69
    allery
    -0.68
     Columbia
    -0.67
     Goff
    -0.67
     Crossref
    -0.65
    âĢ¢âĢ¢
    -0.63
     Stellar
    -0.63
    POSITIVE LOGITS
    hens
    1.34
    seekers
    0.96
    waves
    0.95
    hen
    0.94
    wave
    0.92
    stroke
    0.86
     oven
    0.85
    heat
    0.84
    bender
    0.80
     heat
    0.80
    Activations Density 0.021%

    No Known Activations