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. 10-RES-JB
    6. 263
    Prev
    Next
    INDEX
    Explanations

    actions or events that have occurred or been completed

    oai_token-act-pair · gpt-3.5-turbo

    actions or states of having occurred in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RB
    -0.70
    quel
    -0.64
    uesday
    -0.62
    razil
    -0.62
    cour
    -0.61
    hart
    -0.60
    allas
    -0.60
    rish
    -0.59
    HO
    -0.58
    eming
    -0.58
    POSITIVE LOGITS
     sufficiently
    0.97
     previous
    0.97
     previously
    0.93
     enough
    0.88
    enough
    0.88
     hitherto
    0.88
     earlier
    0.88
     beforehand
    0.87
     sufficient
    0.83
    Enough
    0.73
    Activations Density 0.341%

    No Known Activations