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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13895
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "audacity" or boldness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to audio and sound

    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
    TON
    -0.71
    ktop
    -0.68
    OPLE
    -0.67
    ulkan
    -0.66
    FUL
    -0.66
    tons
    -0.65
    WAYS
    -0.65
    theless
    -0.64
     Warfare
    -0.63
     RIS
    -0.63
    POSITIVE LOGITS
    iov
    1.24
    itors
    1.22
    acious
    1.16
    itions
    1.16
    ience
    1.11
    iences
    1.09
    iting
    1.09
    iosyn
    1.09
    yssey
    1.09
    ibly
    1.05
    Activations Density 0.011%

    No Known Activations