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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 2957
    Prev
    Next
    INDEX
    Explanations

    special characters used to emphasize or express strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    repeated symbols or characters within the text

    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
     fishes
    -0.76
     welf
    -0.74
     greens
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
     indemn
    -0.68
    pped
    -0.67
     adulthood
    -0.65
     charger
    -0.65
     nodd
    -0.65
     laun
    -0.65
    POSITIVE LOGITS
    they
    1.01
    WHERE
    1.00
    yet
    0.99
    wait
    0.96
    BUT
    0.94
    etc
    0.91
    there
    0.90
    why
    0.88
    where
    0.87
    yeah
    0.86
    Activations Density 0.039%

    No Known Activations