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. 15380
    Prev
    Next
    INDEX
    Explanations

    parentheses at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in a document

    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
     veget
    -0.79
     flock
    -0.76
     inund
    -0.76
     appropri
    -0.75
     tackling
    -0.72
     drifting
    -0.72
     undet
    -0.72
     pill
    -0.71
     indistinguishable
    -0.71
     overfl
    -0.71
    POSITIVE LOGITS
    â̦)
    1.27
    emphasis
    1.11
    See
    1.09
    ANI
    1.08
    ...)
    1.07
    hide
    1.05
    CBC
    1.05
    Photo
    1.04
    Also
    1.03
    Courtesy
    1.01
    Activations Density 0.050%

    No Known Activations