© 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. 415
    Prev
    Next
    INDEX
    Explanations

    words related to various types of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    the word "activity."

    oai_token-act-pair · gpt-4-turbo

    references to general activity or actions

    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
    oiler
    -0.77
    gling
    -0.73
    uran
    -0.72
     veiled
    -0.68
     passage
    -0.67
     Missile
    -0.67
    ixed
    -0.66
    nai
    -0.66
    este
    -0.64
    cknowled
    -0.63
    POSITIVE LOGITS
     activity
    1.13
     activities
    0.93
     Activity
    0.92
    ername
    0.90
    activity
    0.88
    ivism
    0.84
    uality
    0.82
    ivity
    0.81
    spection
    0.81
    iveness
    0.79
    Activations Density 0.011%

    No Known Activations