© 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. 4-RES-JB
    11. 24167
    Prev
    Next
    INDEX
    Explanations

    book titles

    oai_token-act-pair · gpt-3.5-turbo

    the titles of books or papers

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

    No Comments

    Negative Logits
    undai
    -0.88
    etooth
    -0.80
     trouble
    -0.78
     opponent
    -0.78
     firewall
    -0.78
     shenan
    -0.72
     thrott
    -0.70
     warr
    -0.70
    ikuman
    -0.70
     foe
    -0.70
    POSITIVE LOGITS
     Provided
    0.85
     "âĢ¦
    0.80
    YES
    0.78
    ³³³³³³³³³³³³³³³³
    0.76
     Prelude
    0.76
     "...
    0.76
     Literary
    0.74
    taboola
    0.74
     Whilst
    0.72
     http
    0.71
    Activations Density 0.162%

    No Known Activations