© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16459
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to heights or levels, especially when they are above a certain threshold

    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
    arry
    -0.75
    iasco
    -0.71
    obi
    -0.70
    eddy
    -0.66
    Untitled
    -0.64
     Syndrome
    -0.62
    Orig
    -0.62
     Interview
    -0.61
    iew
    -0.60
     Cust
    -0.59
    POSITIVE LOGITS
     higher
    3.30
    higher
    2.94
    Higher
    2.75
     Higher
    2.60
     lower
    2.32
     highest
    1.81
     greater
    1.78
    lower
    1.73
     high
    1.67
     larger
    1.63
    Activations Density 0.019%

    No Known Activations