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. 16419
    Prev
    Next
    INDEX
    Explanations

    exclamatory expressions or phrases denoting high emotion or urgency

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory statements and strong emotional reactions

    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
    atories
    -0.78
    lining
    -0.68
     path
    -0.67
    roup
    -0.67
    unker
    -0.67
    ativity
    -0.67
    ouf
    -0.66
     outline
    -0.65
    lings
    -0.64
    athering
    -0.64
    POSITIVE LOGITS
    !!!!!
    1.17
    !!!
    1.13
    !!
    1.10
     :-)
    1.00
     :)
    0.91
    9999
    0.90
    !/
    0.90
    ?!
    0.89
    !!!!
    0.87
    @#
    0.85
    Activations Density 0.017%

    No Known Activations