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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16469
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations such as dioceses

    oai_token-act-pair · gpt-3.5-turbo
    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
     brackets
    -0.80
     basket
    -0.69
     NR
    -0.66
    dr
    -0.64
     PP
    -0.64
     Pinterest
    -0.63
     Block
    -0.63
     rockets
    -0.63
     buttons
    -0.63
     Dro
    -0.62
    POSITIVE LOGITS
    ocese
    3.56
    ummer
    1.54
    ouple
    1.29
    arbon
    1.18
    utsche
    1.12
    rosse
    0.96
    uly
    0.90
    cember
    0.88
    hess
    0.88
    bishop
    0.87
    Activations Density 0.028%

    No Known Activations