© 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. 2-RES-JB
    11. 21931
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or accomplishments, especially those related to documented achievements or deeds

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "deed" and its variations

    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
     Lank
    -0.84
    Topics
    -0.71
     Flavoring
    -0.70
    awk
    -0.69
    antha
    -0.65
     sshd
    -0.65
    AU
    -0.64
     Cater
    -0.63
    ĨĴ
    -0.63
    oglu
    -0.63
    POSITIVE LOGITS
     deed
    1.46
     deeds
    1.41
    nect
    0.91
    istically
    0.85
    daq
    0.84
    \\\\\\\\
    0.79
    manship
    0.78
     Machina
    0.78
    keeper
    0.78
    uary
    0.74
    Activations Density 0.012%

    No Known Activations