© 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. 3-RES-JB
    11. 1558
    Prev
    Next
    INDEX
    Explanations

    specific references related to a common theme or entity, possibly something named "Alt" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Alt" or its variants in various contexts

    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
    BLE
    -0.81
    LESS
    -0.75
    EEE
    -0.75
    BILITY
    -0.73
    ãĤ§
    -0.72
    åŃIJ
    -0.68
    ILA
    -0.68
    enegger
    -0.68
    hips
    -0.67
    STD
    -0.67
    POSITIVE LOGITS
    ogether
    1.38
    itude
    1.17
    itud
    1.07
    itudes
    1.06
    uve
    1.06
    imore
    1.00
    itudinal
    0.87
    adena
    0.82
    urous
    0.79
    imately
    0.78
    Activations Density 0.006%

    No Known Activations