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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 20940
    Prev
    Next
    INDEX
    Explanations

    commands or prompts for editing or modifying text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "edit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anthem
    -0.73
    phal
    -0.70
     Huck
    -0.66
     Ballistic
    -0.65
    bestos
    -0.65
    luster
    -0.65
     Starr
    -0.62
     Franch
    -0.61
    ONSORED
    -0.61
    hovah
    -0.60
    POSITIVE LOGITS
    orship
    0.96
     editing
    0.88
     edit
    0.85
    edit
    0.83
     edits
    0.81
    esty
    0.81
    ision
    0.81
    ipedia
    0.80
    itors
    0.75
    ovie
    0.74
    Activations Density 0.026%

    No Known Activations