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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 16566
    Prev
    Next
    INDEX
    Explanations

    the word "charter" at varying degrees of importance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of charter schools and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenberg
    -0.89
     Rove
    -0.79
    nesota
    -0.71
    enez
    -0.69
    aunder
    -0.69
    ewski
    -0.66
    ocate
    -0.65
    swer
    -0.64
    olls
    -0.63
    ugs
    -0.63
    POSITIVE LOGITS
     charter
    0.99
     Charter
    0.91
    iffs
    0.79
    zman
    0.74
    icut
    0.73
    inary
    0.65
     CLIENT
    0.63
    eer
    0.63
     board
    0.63
    iff
    0.62
    Activations Density 0.005%

    No Known Activations