© 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. 4-RES-JB
    11. 6965
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or executions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "carry out."

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

    No Comments

    Negative Logits
    esa
    -0.71
    lua
    -0.69
    edia
    -0.66
     magnets
    -0.64
    hetti
    -0.62
    shaw
    -0.62
     vault
    -0.61
     Room
    -0.61
    BILITY
    -0.60
     Clyde
    -0.58
    POSITIVE LOGITS
    flows
    0.77
     reconnaissance
    0.72
    tan
    0.72
    ãĥ¼ãĥĨãĤ£
    0.70
    utical
    0.70
    ãĥ¼ãĤ¯
    0.70
     surveillance
    0.69
    omorphic
    0.69
    soever
    0.68
    uterte
    0.66
    Activations Density 0.029%

    No Known Activations