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. 5-RES-JB
    6. 9568
    Prev
    Next
    INDEX
    Explanations

    comparisons using the phrase "as something as."

    oai_token-act-pair · gpt-3.5-turbo

    comparisons expressing a degree of similarity or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eri
    -0.76
    Cause
    -0.75
    uld
    -0.71
    ACA
    -0.67
    ainer
    -0.66
    reated
    -0.66
    erial
    -0.63
    ESE
    -0.63
    acent
    -0.63
    cia
    -0.63
    POSITIVE LOGITS
     possible
    0.78
    lihood
    0.77
    pects
    0.76
     ours
    0.75
    ©¶æ
    0.75
    angular
    0.71
    ij士
    0.69
     usual
    0.68
     Compass
    0.68
     practicable
    0.67
    Activations Density 0.094%

    No Known Activations