© 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. 3-RES-JB
    11. 20751
    Prev
    Next
    INDEX
    Explanations

    phrases related to leaving or concluding an activity or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "walked away" or "passed away."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.91
    ums
    -0.75
    annis
    -0.70
     Zeit
    -0.69
    anwhile
    -0.67
    ionic
    -0.65
    oly
    -0.65
    elly
    -0.63
    ummer
    -0.63
     chap
    -0.62
    POSITIVE LOGITS
     away
    0.79
    ADRA
    0.70
    RAG
    0.68
     Away
    0.67
    RAY
    0.65
    à©
    0.65
     waivers
    0.64
    Adult
    0.64
     AW
    0.64
    )=(
    0.62
    Activations Density 0.024%

    No Known Activations