Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14221
    Prev
    Next
    INDEX
    Explanations

    terms related to the action of rewriting or revision

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of rewriting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cent
    -0.74
     Loc
    -0.73
    Med
    -0.69
    ii
    -0.68
    IK
    -0.65
    imb
    -0.64
    ca
    -0.62
     Mt
    -0.62
    lig
    -0.61
    eb
    -0.61
    POSITIVE LOGITS
     rewrite
    3.71
     rewritten
    3.20
     rewriting
    2.82
     remake
    1.36
     redef
    1.31
     reim
    1.22
     Rew
    1.22
     rename
    1.19
    wrote
    1.19
     resh
    1.18
    Activations Density 0.025%

    No Known Activations