© 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. 6-RES-JB
    11. 17011
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational institutions and individuals' names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly related to educational institutions and locations

    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
    WARD
    -0.84
    ences
    -0.79
    lund
    -0.77
    ports
    -0.75
    enced
    -0.71
    itives
    -0.70
    pring
    -0.69
    ITED
    -0.69
    inals
    -0.68
    ALLY
    -0.68
    POSITIVE LOGITS
    bara
    1.00
    anooga
    0.89
    plain
    0.86
    bones
    0.86
    ron
    0.75
    agne
    0.75
    unin
    0.75
    illin
    0.75
    bone
    0.74
     DeV
    0.72
    Activations Density 0.051%

    No Known Activations