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. 5181
    Prev
    Next
    INDEX
    Explanations

    words related to location, particularly where someone is originally from

    oai_token-act-pair · gpt-3.5-turbo

    instances of origin or place of belonging

    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
    idav
    -0.67
    ercise
    -0.67
    aminer
    -0.65
    awatts
    -0.63
    EPA
    -0.61
    needed
    -0.60
    Assistant
    -0.59
    awaited
    -0.59
     releases
    -0.58
    release
    -0.58
    POSITIVE LOGITS
     afar
    0.87
     abroad
    0.83
     rural
    0.79
     nowhere
    0.78
     humble
    0.77
     poorer
    0.76
    angu
    0.75
     overseas
    0.74
     affluent
    0.74
     wealthy
    0.72
    Activations Density 0.104%

    No Known Activations