© 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. 1-RES-JB
    11. 23379
    Prev
    Next
    INDEX
    Explanations

    phrases related to rewriting or revision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rewrite" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ells
    -0.80
    ello
    -0.70
    amina
    -0.70
    Sea
    -0.68
    ²
    -0.67
    apolis
    -0.66
    spot
    -0.65
    apa
    -0.65
    ¬¼
    -0.65
    rug
    -0.65
    POSITIVE LOGITS
     rewrite
    1.44
     rewritten
    1.41
     rewriting
    1.19
     rethink
    0.83
     restruct
    0.79
    é»Ĵ
    0.79
    inition
    0.78
     guiActiveUn
    0.77
     raping
    0.76
    RFC
    0.76
    Activations Density 0.007%

    No Known Activations