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. 14104
    Prev
    Next
    INDEX
    Explanations

    instances where the word "consultation" or its variations appear in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to public consultations

    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
    ante
    -0.72
    Breaking
    -0.67
     Runner
    -0.67
    Run
    -0.67
     Run
    -0.64
    aday
    -0.63
    ach
    -0.63
    rue
    -0.63
    erer
    -0.63
    buck
    -0.63
    POSITIVE LOGITS
     consultation
    3.85
     consultations
    2.74
     consult
    1.85
     consulted
    1.62
     Consult
    1.61
     consulting
    1.52
     collaboration
    1.22
     appointment
    1.21
     coordination
    1.18
     consultancy
    1.18
    Activations Density 0.013%

    No Known Activations