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. 12719
    Prev
    Next
    INDEX
    Explanations

    text related to desires or preferences expressed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or willingness

    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
    ulty
    -0.68
    livious
    -0.67
    igmatic
    -0.67
    errors
    -0.66
    semble
    -0.65
    VERTISEMENT
    -0.65
    ilings
    -0.64
    hesis
    -0.62
    ccording
    -0.61
    soDeliveryDate
    -0.60
    POSITIVE LOGITS
     revenge
    0.95
     nothing
    0.84
    reprene
    0.82
     to
    0.82
    only
    0.78
     answers
    0.75
     something
    0.75
     desperately
    0.71
     attention
    0.70
     vengeance
    0.68
    Activations Density 0.099%

    No Known Activations