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. 9-RES-JB
    6. 3973
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the consequences or effects of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.77
    stra
    -0.75
     Rated
    -0.73
    atu
    -0.70
    itsch
    -0.70
    iazep
    -0.66
    zb
    -0.66
    tex
    -0.66
    schild
    -0.64
     Marketable
    -0.64
    POSITIVE LOGITS
     havoc
    1.40
     trouble
    1.08
     mayhem
    1.07
     confusion
    1.07
     headaches
    1.06
     undue
    0.98
     panic
    0.95
     unnecessary
    0.92
     friction
    0.92
     upheaval
    0.91
    Activations Density 0.058%

    No Known Activations