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. 12963
    Prev
    Next
    INDEX
    Explanations

    references to illegal or unauthorized actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illegal activities or actions

    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
    ĸļ
    -0.79
    orem
    -0.74
     Seasons
    -0.73
    roth
    -0.73
    oleon
    -0.70
    hum
    -0.70
    alg
    -0.69
     enthus
    -0.68
    erer
    -0.67
    iments
    -0.66
    POSITIVE LOGITS
     detained
    0.84
     downloaded
    0.77
     obtained
    0.75
     planted
    0.74
     copied
    0.74
     intercepted
    0.72
    reated
    0.72
     unloaded
    0.71
     resided
    0.71
     downloading
    0.71
    Activations Density 0.031%

    No Known Activations