© 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. 23391
    Prev
    Next
    INDEX
    Explanations

    names of legal documents or legal terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "pt" within words, indicating a focus on specific terms or abbreviations

    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
     Bravo
    -0.76
    hold
    -0.71
     resil
    -0.70
     Carib
    -0.70
    HAHA
    -0.69
    BIP
    -0.68
    é¾įåĸļ士
    -0.67
    awaru
    -0.66
     Witcher
    -0.65
    HAHAHAHA
    -0.64
    POSITIVE LOGITS
    rees
    1.06
    itude
    1.02
    raction
    0.98
    ember
    0.98
    onent
    0.96
    ools
    0.94
    icket
    0.94
    uple
    0.91
    acular
    0.91
    enium
    0.89
    Activations Density 0.009%

    No Known Activations