© 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. 12658
    Prev
    Next
    INDEX
    Explanations

    website hyperlinks or clickable paths

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a special character or paragraph marker indicating formatting in text

    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
    wagen
    -0.70
     casting
    -0.68
     detached
    -0.67
     guarding
    -0.67
     relocation
    -0.64
     dirt
    -0.64
     exhaustion
    -0.64
     maximizing
    -0.64
     pressing
    -0.63
     walking
    -0.63
    POSITIVE LOGITS
    £
    1.11
    ¹
    1.09
    ¡
    1.01
    Į
    1.01
    ¤
    0.98
    º
    0.97
    ¯
    0.96
    į
    0.95
    ı
    0.93
    Ĭ
    0.89
    Activations Density 0.379%

    No Known Activations