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. 2-RES-JB
    6. 20169
    Prev
    Next
    INDEX
    Explanations

    dates and locations referring to places where someone was born

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Born" and its variations, often in the context of birth or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dfx
    -0.86
    aito
    -0.74
    ioxide
    -0.74
    ably
    -0.68
    atic
    -0.68
    andum
    -0.67
    olicy
    -0.66
    ifling
    -0.65
     Monica
    -0.64
     Blackwell
    -0.59
    POSITIVE LOGITS
     Born
    1.04
    stellar
    0.98
    Born
    0.95
    waters
    0.89
    emis
    0.81
    blood
    0.76
    born
    0.74
    bones
    0.73
    nesses
    0.73
    abouts
    0.72
    Activations Density 0.010%

    No Known Activations