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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21714
    Prev
    Next
    INDEX
    Explanations

    human names and titles

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or segments in proper names and nouns

    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
    ongyang
    -0.74
    é»Ĵ
    -0.69
    ccording
    -0.67
     WATCHED
    -0.65
     brackets
    -0.65
    HAEL
    -0.63
    ebted
    -0.63
    PDATE
    -0.62
    ãĥ©ãĥ³
    -0.61
    AUD
    -0.61
    POSITIVE LOGITS
    enment
    0.99
    ciating
    0.74
    deen
    0.70
    igans
    0.66
    ury
    0.65
    ende
    0.64
     Zeit
    0.63
    enko
    0.61
    gae
    0.61
    shire
    0.61
    Activations Density 0.397%

    No Known Activations