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. 5979
    Prev
    Next
    INDEX
    Explanations

    SQL query commands

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically parentheses and brackets

    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
    vell
    -0.81
    ses
    -0.81
    duction
    -0.76
    ardless
    -0.76
    atures
    -0.75
    matic
    -0.75
    Gall
    -0.72
    Reviewer
    -0.71
    hent
    -0.70
    ionic
    -0.70
    POSITIVE LOGITS
    ))))
    0.85
    ;;;;;;;;
    0.82
    ;;;;;;;;;;;;
    0.79
     ¶
    0.76
    ::::::::
    0.74
    ::::
    0.70
     {\
    0.67
     Colon
    0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.65
     ENG
    0.64
    Activations Density 0.030%

    No Known Activations