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. 1140
    Prev
    Next
    INDEX
    Explanations

    phrases indicating encouragement or urgency

    oai_token-act-pair · gpt-3.5-turbo

    expressions of exasperation and rhetorical questioning

    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
    isk
    -0.63
    ãĤ±
    -0.62
    isen
    -0.61
     sled
    -0.61
     roots
    -0.60
    Prev
    -0.58
    CV
    -0.58
    itory
    -0.58
    lishes
    -0.57
    Els
    -0.57
    POSITIVE LOGITS
     Lah
    0.73
     thou
    0.68
     pity
    0.68
     Gaw
    0.67
     Anyway
    0.67
     Jinn
    0.67
    ij士
    0.65
     Beware
    0.63
     beware
    0.62
     Defender
    0.62
    Activations Density 0.420%

    No Known Activations