© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 728
    Prev
    Next
    INDEX
    Explanations

    expressions related to communication and interaction among individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or symbols that could imply emphasis or frustration in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.76
     topic
    -0.76
     mathemat
    -0.73
     limb
    -0.72
     dossier
    -0.70
     invention
    -0.68
     detail
    -0.68
     territorial
    -0.68
    eatures
    -0.68
     landmarks
    -0.68
    POSITIVE LOGITS
    ï¸ı
    1.24
    there
    0.95
    ï¸
    0.94
    RIP
    0.89
    ãĥĥãĥī
    0.88
    nob
    0.87
    then
    0.84
    âĹ¼
    0.83
    everyone
    0.83
    lean
    0.83
    Activations Density 0.030%

    No Known Activations