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. 4630
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences beginning with the word "Again"

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "Again" and phrases that emphasize continuity or recurrence

    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
    kees
    -0.72
    emo
    -0.64
     Cooldown
    -0.64
    aila
    -0.60
     Defender
    -0.59
     Clouds
    -0.58
    retty
    -0.57
     Fell
    -0.57
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.56
    intel
    -0.56
    POSITIVE LOGITS
    dor
    0.70
    ãĥīãĥ©ãĤ´ãĥ³
    0.68
     emphasis
    0.66
    IFIED
    0.64
    048
    0.63
    ierre
    0.63
    ortmund
    0.62
     blur
    0.62
    ukong
    0.61
    ãģ®å®
    0.61
    Activations Density 0.109%

    No Known Activations