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. 8-RES-JB
    6. 2876
    Prev
    Next
    INDEX
    Explanations

    specific references to a group of people

    oai_token-act-pair · gpt-3.5-turbo

    references to a group of people or collective subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Eleven
    -0.79
    CCC
    -0.77
     Phi
    -0.70
    Rating
    -0.63
    DAY
    -0.63
    JD
    -0.62
     Amen
    -0.61
    Govern
    -0.61
     Sirius
    -0.60
     Atlantis
    -0.59
    POSITIVE LOGITS
    're
    1.32
    'll
    1.12
    zbollah
    1.11
    selves
    1.08
    've
    1.07
    gemony
    0.98
    'd
    0.92
     may
    0.92
    pherd
    0.91
     shouldn
    0.88
    Activations Density 0.180%

    No Known Activations