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. 299
    Prev
    Next
    INDEX
    Explanations

    strong verbs related to firm actions or convictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being trapped or identified in a difficult situation

    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
     transient
    -0.69
     register
    -0.68
     nickname
    -0.63
     PCR
    -0.63
     alias
    -0.63
    RESULTS
    -0.62
     attraction
    -0.61
     topic
    -0.61
     nephew
    -0.60
     1993
    -0.60
    POSITIVE LOGITS
     nailed
    2.47
     screwed
    2.36
     outlined
    1.62
     fucked
    1.43
     hammered
    1.30
     messed
    1.23
     bolted
    1.14
     drilled
    1.08
     baked
    1.01
     perfected
    0.97
    Activations Density 0.033%

    No Known Activations