© 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. 23703
    Prev
    Next
    INDEX
    Explanations

    instances where the document discusses the speaker, potentially involving personal opinions, experiences, or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to personal identity or self

    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
     Us
    -0.69
     Towns
    -0.64
     Governments
    -0.59
    Args
    -0.59
     us
    -0.59
    earable
    -0.59
     Confederation
    -0.58
     Entity
    -0.58
     Rolls
    -0.58
     ours
    -0.57
    POSITIVE LOGITS
    adows
    1.31
    lees
    1.27
    adow
    1.20
    andering
    1.18
    zzo
    1.09
     personally
    1.08
    gal
    1.08
    ander
    0.94
    imei
    0.94
    ek
    0.93
    Activations Density 0.103%

    No Known Activations