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. 8-RES-JB
    6. 21266
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or objectives that need to be accomplished

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    typ
    -0.68
     newsp
    -0.66
     millenn
    -0.65
     Caller
    -0.63
    arching
    -0.58
    quickShipAvailable
    -0.57
     seams
    -0.56
     pandemonium
    -0.56
    mining
    -0.56
     Execution
    -0.55
    POSITIVE LOGITS
     emulate
    1.05
     be
    0.97
     adopt
    0.97
     participate
    0.94
     take
    0.94
     partake
    0.93
     pursue
    0.91
     incorporate
    0.91
     observe
    0.91
     overcome
    0.91
    Activations Density 0.126%

    No Known Activations