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. 1708
    Prev
    Next
    INDEX
    Explanations

    phrases related to thoughts or considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the concept of "minds" along with various associated relationships

    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
    wcsstore
    -0.88
    assium
    -0.78
    buster
    -0.73
    ucc
    -0.72
    itsch
    -0.72
    arat
    -0.70
    Matrix
    -0.69
    ................................................................
    -0.68
    iasm
    -0.67
    WARE
    -0.67
    POSITIVE LOGITS
     individuals
    1.09
     strangers
    0.96
     citizens
    0.95
     those
    0.94
     passers
    0.91
     bystanders
    0.91
     mortals
    0.91
     unsuspecting
    0.89
     countless
    0.89
     persons
    0.86
    Activations Density 0.170%

    No Known Activations