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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 12169
    Prev
    Next
    INDEX
    Explanations

    verbs related to cranking or turning something

    oai_token-act-pair · gpt-3.5-turbo

    words and variations related to the action of cranking or spankings

    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
     Bett
    -0.71
    gur
    -0.66
    nsic
    -0.65
    Interstitial
    -0.63
     Niet
    -0.63
     Guardians
    -0.62
     Eid
    -0.62
    tnc
    -0.60
    glass
    -0.59
    akh
    -0.59
    POSITIVE LOGITS
     crank
    0.94
    lists
    0.84
    haw
    0.80
    chairs
    0.77
    manship
    0.76
    bike
    0.76
    erous
    0.72
    arthed
    0.72
    ular
    0.71
    ocobo
    0.71
    Activations Density 0.034%

    No Known Activations