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. 14645
    Prev
    Next
    INDEX
    Explanations

    terms related to ambition or ambitious actions

    oai_token-act-pair · gpt-3.5-turbo

    references to ambitious plans or goals

    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
     minus
    -0.77
     versus
    -0.68
     vs
    -0.68
     wash
    -0.66
    occ
    -0.64
    /
    -0.62
     RIP
    -0.60
    circ
    -0.60
     rec
    -0.59
    boro
    -0.59
    POSITIVE LOGITS
     ambitious
    3.49
    bitious
    2.28
     ambition
    2.03
     adventurous
    1.60
     ambitions
    1.59
     lofty
    1.46
     imaginative
    1.38
     extravagant
    1.38
     aspiring
    1.37
     ingenious
    1.37
    Activations Density 0.025%

    No Known Activations