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. 9-RES-JB
    6. 11627
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of being "aware" is mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aware."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retri
    -0.57
     reunion
    -0.56
     reun
    -0.55
    cific
    -0.55
    entry
    -0.54
    cell
    -0.53
    irrel
    -0.53
    emetery
    -0.53
    bard
    -0.52
     coord
    -0.51
    POSITIVE LOGITS
    ledged
    1.17
    ledge
    0.97
     thereof
    0.95
     of
    0.93
    clinton
    0.79
    Of
    0.79
    ial
    0.77
    of
    0.73
     OF
    0.71
    aking
    0.71
    Activations Density 0.048%

    No Known Activations