© 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. 7053
    Prev
    Next
    INDEX
    Explanations

    phrases prompting actions or interactions, often involving sharing with others

    oai_token-act-pair · gpt-3.5-turbo

    commands and requests for information sharing

    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
    Ö¼
    -0.68
    opes
    -0.65
     comparatively
    -0.63
    ©¶æ¥µ
    -0.62
     admittedly
    -0.61
    £ı
    -0.59
    à¨
    -0.59
    ensibly
    -0.58
    itled
    -0.57
    going
    -0.57
    POSITIVE LOGITS
     us
    1.41
     me
    1.30
     yourself
    1.22
     yourselves
    1.11
     Yourself
    1.06
     your
    0.99
     someone
    0.99
     others
    0.99
     Us
    0.98
    someone
    0.93
    Activations Density 0.197%

    No Known Activations