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. 0-RES-JB
    6. 9145
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical and political annexation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ethnicity and territorial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAW
    -0.76
     RUN
    -0.72
     Puzz
    -0.71
    sic
    -0.69
     ..............
    -0.69
    ATTLE
    -0.66
    ADRA
    -0.66
    Santa
    -0.65
    kson
    -0.64
     Sao
    -0.64
    POSITIVE LOGITS
     ethn
    1.13
    ikan
    0.80
    idth
    0.67
    oby
    0.66
    yg
    0.65
     indent
    0.65
     aut
    0.65
    audi
    0.64
    illac
    0.63
    umblr
    0.62
    Activations Density 0.001%

    No Known Activations