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. 596
    Prev
    Next
    INDEX
    Explanations

    words related to specific groups of people such as residents of various places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific national or regional identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    demonyms referring to residents of specific regions or places.

    oai_token-act-pair · gpt-4oTriggered by @tatsatx
    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
    struct
    -0.69
    ctor
    -0.67
    ring
    -0.66
    Chain
    -0.63
    Initialized
    -0.61
    icer
    -0.61
    efully
    -0.60
    mination
    -0.60
    leader
    -0.59
    staff
    -0.59
    POSITIVE LOGITS
     voted
    0.90
     rejoice
    0.83
     alike
    0.81
     living
    0.76
     enjoy
    0.75
    '
    0.75
     awoke
    0.75
    hip
    0.74
     deserve
    0.73
     clam
    0.73
    Activations Density 0.167%

    No Known Activations