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. 7-RES-JB
    6. 746
    Prev
    Next
    INDEX
    Explanations

    words related to providing or offering something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of providing or supplying something essential or beneficial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brow
    -0.71
    bel
    -0.67
    bold
    -0.65
    blade
    -0.64
    mat
    -0.64
    doms
    -0.64
    doctor
    -0.64
    ignore
    -0.63
    walker
    -0.63
    war
    -0.63
    POSITIVE LOGITS
    utical
    1.07
     insight
    0.90
     sust
    0.88
     ample
    0.87
     invaluable
    0.82
     logistical
    0.82
     refunds
    0.79
     condolences
    0.78
     insights
    0.76
     us
    0.75
    Activations Density 0.043%

    No Known Activations