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

    Neuronpedia

    APICircuit 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. 16751
    Prev
    Next
    INDEX
    Explanations

    dates presented in a certain format

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly semicolons

    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
     unnecess
    -0.87
    agic
    -0.78
    stration
    -0.78
    din
    -0.75
     psychiat
    -0.69
     helicop
    -0.68
    senal
    -0.68
     destro
    -0.67
    enium
    -0.66
    ront
    -0.66
    POSITIVE LOGITS
    -)
    1.11
    alias
    0.89
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.81
     alternatively
    0.76
     cf
    0.75
    ;;;;;;;;;;;;
    0.71
     Editing
    0.69
    âĢ¢âĢ¢
    0.66
     partName
    0.65
     thence
    0.65
    Activations Density 0.046%

    No Known Activations