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. 18136
    Prev
    Next
    INDEX
    Explanations

    mentions of specific historical or biblical figures

    oai_token-act-pair · gpt-3.5-turbo

    references to historical or religious figures and texts

    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
    arial
    -0.84
    orie
    -0.78
    neau
    -0.78
    pick
    -0.77
    ifact
    -0.77
    rien
    -0.76
    rier
    -0.76
    ice
    -0.73
    arette
    -0.73
    aci
    -0.71
    POSITIVE LOGITS
    theless
    0.77
     Moses
    0.77
    frey
    0.76
     Runes
    0.74
    heed
    0.70
     Parish
    0.67
     Rebirth
    0.66
     Malone
    0.66
    ÄŁ
    0.64
     mythology
    0.64
    Activations Density 0.036%

    No Known Activations