© 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 EvalsExportsinterp-engineNEWAPI 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. 9280
    Prev
    Next
    INDEX
    Explanations

    instances of the word "command" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "command" and its variations

    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
     Happ
    -0.69
    OHN
    -0.67
     Bloom
    -0.66
    rencies
    -0.65
     Boys
    -0.65
    Mini
    -0.63
    Bloom
    -0.62
    Polit
    -0.62
    Prev
    -0.61
    ï¸
    -0.61
    POSITIVE LOGITS
    eering
    1.27
    eer
    1.13
    eers
    1.08
    aining
    0.95
    nance
    0.84
     commanded
    0.84
    ership
    0.84
    ments
    0.84
     commands
    0.83
    ained
    0.83
    Activations Density 0.026%

    No Known Activations