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. 10-RES-JB
    6. 21261
    Prev
    Next
    INDEX
    Explanations

    German verbs with the prefix 'ver-' related to actions or developments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'w'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blossom
    -0.62
    terday
    -0.61
     appendix
    -0.57
     Bravo
    -0.57
     absence
    -0.56
     flashbacks
    -0.55
    staking
    -0.55
     PLAN
    -0.54
     fracture
    -0.54
     jealousy
    -0.53
    POSITIVE LOGITS
    ür
    1.04
    ohl
    1.02
    erk
    0.98
    irts
    0.98
    ollen
    0.96
    arten
    0.94
    ijn
    0.93
    ör
    0.92
    icht
    0.91
    aren
    0.89
    Activations Density 0.044%

    No Known Activations