© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18612
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Baidu" and its related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to platforms or types of support related to online content or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansk
    -0.73
    ials
    -0.68
    nance
    -0.68
    cius
    -0.68
    inem
    -0.66
    imens
    -0.66
    ific
    -0.65
    gress
    -0.62
    ittance
    -0.62
    elling
    -0.62
    POSITIVE LOGITS
    alos
    0.64
    Stage
    0.61
    GROUP
    0.60
     Marketable
    0.57
    isi
    0.56
    emouth
    0.56
    tips
    0.56
    hig
    0.56
    °
    0.55
    ovember
    0.55
    Activations Density 0.177%

    No Known Activations