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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 4704
    Prev
    Next
    INDEX
    Explanations

    past tense action verbs related to sports or competitions

    oai_token-act-pair · gpt-3.5-turbo

    words related to the verb "come" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.70
     Scotia
    -0.63
    cean
    -0.61
    shown
    -0.60
     Ital
    -0.59
    Discuss
    -0.57
     Coil
    -0.56
     ÃĹ
    -0.56
    asio
    -0.56
    vez
    -0.56
    POSITIVE LOGITS
     roaring
    0.93
    backs
    0.88
     off
    0.87
     crashing
    0.82
     closest
    0.81
     alive
    0.81
     undone
    0.78
     awfully
    0.77
     aboard
    0.76
     close
    0.74
    Activations Density 0.042%

    No Known Activations