Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24019
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "hem"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific communities or groups within society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Explosive
    -0.60
     Unlock
    -0.57
     Intelligent
    -0.57
     firing
    -0.57
     iP
    -0.56
     jungle
    -0.56
     stock
    -0.56
     packets
    -0.55
     unfl
    -0.55
     charger
    -0.55
    POSITIVE LOGITS
    hem
    5.03
    hemy
    2.18
    hemat
    1.65
    hern
    1.40
    hen
    1.32
    hel
    1.31
    het
    1.29
    hew
    1.21
    hemoth
    1.21
    he
    1.19
    Activations Density 0.018%

    No Known Activations