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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 21473
    Prev
    Next
    INDEX
    Explanations

    adjectives describing attributes or skills

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal attributes and qualifications

    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
    edIn
    -0.76
    adow
    -0.73
    Release
    -0.65
    bda
    -0.62
    EE
    -0.62
    outube
    -0.58
    AY
    -0.58
    æī
    -0.57
    vae
    -0.57
     Release
    -0.56
    POSITIVE LOGITS
     necessary
    1.27
    liest
    1.19
     requisite
    1.14
     needed
    1.13
    iest
    1.03
    needed
    0.99
     required
    0.99
    same
    0.97
    necessary
    0.91
     desired
    0.91
    Activations Density 0.340%

    No Known Activations