© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7119
    Prev
    Next
    INDEX
    Explanations

    words related to actions that involve control, alteration, or influence

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles, indicating ongoing actions or processes

    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
    omet
    -0.69
    spot
    -0.67
    eva
    -0.63
    sv
    -0.62
     flowing
    -0.61
     cropped
    -0.58
     flown
    -0.57
    behind
    -0.57
     unc
    -0.57
    fur
    -0.56
    POSITIVE LOGITS
    redients
    1.02
    HAM
    0.87
    tons
    0.83
    aukee
    0.82
    ADRA
    0.78
    utical
    0.77
    ulate
    0.76
    pole
    0.76
    enance
    0.75
    rarily
    0.73
    Activations Density 0.110%

    No Known Activations