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. 6734
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to lighting up or being lit up

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with the concept of "lighting up" or "firing up" something, often in a metaphorical or motivational context

    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
     Abbas
    -0.72
     Geh
    -0.72
    ayer
    -0.72
    Anne
    -0.69
    len
    -0.68
    ught
    -0.67
    wan
    -0.66
    _>
    -0.66
    leans
    -0.65
    areth
    -0.64
    POSITIVE LOGITS
    draft
    0.77
    cycles
    0.77
    acebook
    0.76
     fists
    0.76
    othal
    0.71
    amac
    0.71
    river
    0.71
    grading
    0.71
     tables
    0.70
    dates
    0.68
    Activations Density 0.065%

    No Known Activations