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. 0-RES-JB
    6. 24117
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or codes within text

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.89
    lihood
    -0.80
    aughs
    -0.74
    cest
    -0.72
    inctions
    -0.69
    owship
    -0.68
    bons
    -0.66
    negie
    -0.64
     Presence
    -0.64
    lehem
    -0.64
    POSITIVE LOGITS
    ãĤ®
    0.84
    reve
    0.68
    Recomm
    0.66
    æ°
    0.66
    ãĤ°
    0.65
    ITS
    0.64
    ãĤ¸
    0.63
    ãĤ·ãĥ£
    0.63
     Britt
    0.61
    ãģ®éŃĶ
    0.61
    Activations Density 0.000%

    No Known Activations