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. 20946
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrasts or antonyms

    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
    lished
    -0.83
    zeb
    -0.82
    ufact
    -0.80
     Mush
    -0.76
     Annotations
    -0.76
    uala
    -0.75
    ondon
    -0.72
    atche
    -0.71
    beans
    -0.69
    anches
    -0.68
    POSITIVE LOGITS
     approach
    0.76
    icter
    0.74
     minded
    0.74
    etheless
    0.74
     scenario
    0.72
    isphere
    0.71
     gender
    0.70
     side
    0.70
    osite
    0.69
    =#
    0.68
    Activations Density 0.020%

    No Known Activations