© 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. 10-RES-JB
    11. 22110
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "which" followed by additional information or context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "which" indicating clauses or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.70
    politics
    -0.65
     Bed
    -0.64
     Bedford
    -0.62
     Schne
    -0.60
     Tanz
    -0.59
    STE
    -0.56
    MENTS
    -0.54
    cking
    -0.53
     Nights
    -0.53
    POSITIVE LOGITS
    soever
    0.95
     comprises
    0.95
     includes
    0.91
     incidentally
    0.91
     consists
    0.87
     enables
    0.85
     involves
    0.85
     contains
    0.84
     resulted
    0.84
     necess
    0.83
    Activations Density 0.068%

    No Known Activations