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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 16917
    Prev
    Next
    INDEX
    Explanations

    ethnicities or nationalities mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ethnic groups and their social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ],"
    -0.60
    `.
    -0.58
    EGIN
    -0.56
    ndum
    -0.54
    î
    -0.54
    ".
    -0.54
    $.
    -0.54
     âĢİ
    -0.53
    ratom
    -0.53
    '.
    -0.51
    POSITIVE LOGITS
     meanwhile
    0.91
     however
    0.71
    sequently
    0.64
    beit
    0.64
     includes
    0.59
     ratios
    0.59
     moreover
    0.59
     Bits
    0.58
     tends
    0.57
     consists
    0.57
    Activations Density 1.536%

    No Known Activations