© 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. 2-RES-JB
    11. 5693
    Prev
    Next
    INDEX
    Explanations

    words related to intactness or preservation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the state of being undamaged or preserved

    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
    ioxide
    -0.79
    gee
    -0.71
    Clar
    -0.70
    ker
    -0.70
    Ku
    -0.68
    cause
    -0.67
    yah
    -0.67
    Stars
    -0.66
    bull
    -0.66
    apter
    -0.66
    POSITIVE LOGITS
     intact
    1.34
     preserved
    0.83
     survives
    0.80
     unchanged
    0.78
    ibility
    0.74
    sburg
    0.73
    İĭ
    0.72
     retaining
    0.72
    ©¶æ¥µ
    0.72
     salvage
    0.71
    Activations Density 0.005%

    No Known Activations