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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9536
    Prev
    Next
    INDEX
    Explanations

    names, particularly last names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.59
     [];
    -0.56
    reau
    -0.53
    VB
    -0.52
    ãĥ¯
    -0.52
    sburgh
    -0.52
    INA
    -0.52
    ruary
    -0.52
    075
    -0.50
    inus
    -0.50
    POSITIVE LOGITS
    ibaba
    0.65
     Hasan
    0.59
    akh
    0.57
    omaly
    0.56
    azi
    0.52
    utsch
    0.52
     Holocaust
    0.51
    bg
    0.51
    ulk
    0.50
     Muslims
    0.49
    Activations Density 0.149%

    No Known Activations