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. 6-RES-JB
    6. 16495
    Prev
    Next
    INDEX
    Explanations

    keywords related to sports reporting

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that indicate continuation or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ®
    -0.83
    \">
    -0.76
     photoc
    -0.73
     NGOs
    -0.72
     condoms
    -0.71
     paed
    -0.70
     sett
    -0.69
     para
    -0.67
     anten
    -0.66
     NGO
    -0.66
    POSITIVE LOGITS
    juries
    1.21
     preseason
    1.16
     offseason
    1.15
     Rookie
    1.15
    ESPN
    1.13
     Heisman
    1.09
    NFL
    1.09
     ESPN
    1.09
    ichick
    1.08
     Playoff
    1.07
    Activations Density 0.719%

    No Known Activations