© 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. 18754
    Prev
    Next
    INDEX
    Explanations

    pronouns and questions related to personal beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to personal identity or relationships

    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
    opens
    -0.79
    accompan
    -0.75
    answered
    -0.70
    ufact
    -0.69
    ī
    -0.64
    ansas
    -0.63
    itiz
    -0.62
    handled
    -0.61
    aby
    -0.61
    PDATE
    -0.61
    POSITIVE LOGITS
     owe
    1.23
     deserve
    1.20
     intend
    1.12
     belong
    1.10
     need
    1.10
     mean
    1.10
     want
    1.06
     qualify
    1.02
     realise
    1.01
     know
    1.00
    Activations Density 0.103%

    No Known Activations