© 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. 7-RES-JB
    11. 21128
    Prev
    Next
    INDEX
    Explanations

    phrases indicating taking control or responsibility over something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the term "take over."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Forward
    -0.68
    Scale
    -0.68
    Bi
    -0.66
    mpeg
    -0.63
    Son
    -0.63
    ////////////////////////////////
    -0.63
    tu
    -0.62
    uten
    -0.61
     Lastly
    -0.60
     Detect
    -0.60
    POSITIVE LOGITS
     reins
    0.76
    lord
    0.75
    tones
    0.73
    erto
    0.72
    respons
    0.70
    drive
    0.70
    ordinate
    0.69
    rule
    0.69
     responsibility
    0.69
    arching
    0.68
    Activations Density 0.034%

    No Known Activations