© 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. 11-RES-JB
    11. 16736
    Prev
    Next
    INDEX
    Explanations

    proper nouns, potentially related to technology or current events

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unheard
    -0.35
     alike
    -0.33
     interchange
    -0.32
     fame
    -0.32
     hover
    -0.31
     grazing
    -0.31
     alternating
    -0.31
     heating
    -0.30
     nonexistent
    -0.30
     replacing
    -0.30
    POSITIVE LOGITS
    ß
    0.44
    ÿ
    0.43
    ğ
    0.43
    Đ
    0.43
    õ
    0.43
    ė
    0.43
    é¾įå¥
    0.43
    ÷
    0.43
    0.43
    ĝ
    0.43
    Activations Density 2.746%

    No Known Activations