© 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. 10058
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "said."

    oai_token-act-pair · gpt-3.5-turbo

    punctuated clauses or phrases that convey significant statements or assertions

    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
    DAQ
    -0.65
    iral
    -0.59
    oin
    -0.59
    iest
    -0.58
    FG
    -0.58
    inar
    -0.57
    !'
    -0.57
    heid
    -0.56
    oward
    -0.56
    aled
    -0.54
    POSITIVE LOGITS
     "'
    1.46
     "[
    1.46
     "...
    1.37
     "âĢ¦
    1.37
     "(
    1.27
     "
    1.25
     "_
    1.24
     ""
    1.14
     '[
    1.13
     ''
    1.11
    Activations Density 0.160%

    No Known Activations