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. 8-RES-JB
    6. 2903
    Prev
    Next
    INDEX
    Explanations

    words related to the name "ain"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Sain" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.67
    trop
    -0.65
    odynam
    -0.65
    nesday
    -0.65
    RNA
    -0.64
    orer
    -0.64
    arser
    -0.64
    RESULTS
    -0.64
    illation
    -0.62
    RN
    -0.62
    POSITIVE LOGITS
    thood
    1.21
    fo
    1.09
    tenance
    1.05
    esville
    0.94
    ese
    0.94
    bow
    0.92
    ees
    0.91
    cia
    0.88
    ee
    0.86
    sts
    0.85
    Activations Density 0.049%

    No Known Activations