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. 14880
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical or political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly those with the name "Caesar" or related to historical and contemporary figures

    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
    pring
    -0.89
    ochond
    -0.82
    rike
    -0.81
    caster
    -0.80
    tip
    -0.79
    ritch
    -0.79
    WARD
    -0.79
    rien
    -0.78
    roe
    -0.78
    ringe
    -0.77
    POSITIVE LOGITS
    esar
    1.05
     Clown
    1.04
     Augustus
    0.82
     Caesar
    0.79
     Chavez
    0.75
     Ventura
    0.74
     Flags
    0.74
     Brut
    0.74
     Reaper
    0.71
     Nig
    0.70
    Activations Density 0.033%

    No Known Activations