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. 379
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names that things are named after

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate naming or honoring someone or something

    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
    ylene
    -0.82
    atisf
    -0.77
    eat
    -0.77
     escalate
    -0.76
     mediated
    -0.72
     inhibits
    -0.71
    xc
    -0.70
    heric
    -0.70
    iot
    -0.70
    igi
    -0.68
    POSITIVE LOGITS
     Sanskrit
    0.83
     Revival
    0.78
     Franch
    0.76
     Herbert
    0.75
     initials
    0.74
     Scots
    0.73
     Him
    0.73
     Guth
    0.73
     Lore
    0.72
     Lincoln
    0.72
    Activations Density 0.072%

    No Known Activations