© 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. 9-RES-JB
    11. 14218
    Prev
    Next
    INDEX
    Explanations

    phrases related to conversations and interactions between individuals, especially focusing on dialogue and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of uncertainty and speculation about events or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seldom
    -0.69
     pleasures
    -0.67
     marvel
    -0.66
     eagerly
    -0.65
     moreover
    -0.65
     adherents
    -0.64
     regularly
    -0.63
    surprisingly
    -0.62
    often
    -0.62
     increasingly
    -0.62
    POSITIVE LOGITS
     [
    1.12
     ['
    0.98
    ),"
    0.94
    ,''
    0.93
    ,'"
    0.93
    .''
    0.87
    ,"
    0.84
     âĢ¦"
    0.82
    .,"
    0.81
    )."
    0.79
    Activations Density 0.848%

    No Known Activations