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. 2326
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used for emphasis

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and special characters

    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
    ©¶æ
    -0.54
     extraord
    -0.47
    stein
    -0.47
     coercive
    -0.45
     affirmative
    -0.45
     racket
    -0.45
    antis
    -0.45
    ously
    -0.44
     hypocritical
    -0.44
     respectively
    -0.44
    POSITIVE LOGITS
     Pastebin
    0.62
     Illum
    0.51
     Grab
    0.50
    itialized
    0.50
     Izan
    0.50
     Patch
    0.49
     Reasons
    0.48
     Scrolls
    0.48
     Athlet
    0.48
     Luck
    0.47
    Activations Density 1.499%

    No Known Activations