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. 22737
    Prev
    Next
    INDEX
    Explanations

    phrases related to music or events

    oai_token-act-pair · gpt-3.5-turbo

    references to tournaments and social events related to singles and prom activities

    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
    iences
    -0.76
    ience
    -0.76
    iveness
    -0.74
    ing
    -0.74
    heses
    -0.73
    essee
    -0.71
    à¼
    -0.70
    interstitial
    -0.70
    ige
    -0.69
    iola
    -0.69
    POSITIVE LOGITS
    creen
    1.01
    hare
    0.80
    BALL
    0.78
    etheus
    0.77
    amples
    0.68
    hift
    0.66
     Ops
    0.65
    querade
    0.65
     Disorder
    0.64
    mun
    0.62
    Activations Density 0.046%

    No Known Activations