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. 18365
    Prev
    Next
    INDEX
    Explanations

    names containing the sequence "ih"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of individuals or characters in a narrative context

    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
    yards
    -0.70
     Predator
    -0.66
    âĸ¬
    -0.65
    mint
    -0.64
     Chips
    -0.63
     Pengu
    -0.61
     Colossus
    -0.60
     Monstrous
    -0.59
    ãĥ¯
    -0.59
     Firefly
    -0.59
    POSITIVE LOGITS
    onen
    1.15
    ollow
    1.04
    ype
    1.00
    ih
    0.99
    ouston
    0.96
    ansen
    0.96
    azard
    0.96
    oney
    0.95
    ackers
    0.93
    awk
    0.93
    Activations Density 0.010%

    No Known Activations