Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7589
    Prev
    Next
    INDEX
    Explanations

    nationalities or ethnicities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or ethnic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chain
    -0.70
    fecture
    -0.69
    Smith
    -0.67
    inventoryQuantity
    -0.66
    ITED
    -0.64
    planet
    -0.61
    ctor
    -0.61
    miss
    -0.60
     confirmation
    -0.60
    efer
    -0.60
    POSITIVE LOGITS
    aurus
    1.16
    paces
    1.11
    ugi
    0.86
    ervatives
    0.86
     who
    0.84
    hip
    0.82
    ktop
    0.81
    ervative
    0.81
    '
    0.80
    omething
    0.80
    Activations Density 0.046%

    No Known Activations