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. 9-RES-JB
    6. 6459
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and medical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to military ranks and organizations, prosthetics, and geographic locations

    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
    numbered
    -0.75
     Bild
    -0.69
     Roe
    -0.65
     Krug
    -0.65
    Tax
    -0.64
     messenger
    -0.63
    cycle
    -0.59
    icals
    -0.58
     Vaugh
    -0.58
    cycles
    -0.56
    POSITIVE LOGITS
    heed
    0.90
    estone
    0.89
    acies
    0.89
    ging
    0.88
    gewater
    0.86
    estones
    0.85
    acity
    0.80
    acus
    0.80
    boa
    0.79
    vernment
    0.79
    Activations Density 0.120%

    No Known Activations