© 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. 18630
    Prev
    Next
    INDEX
    Explanations

    terms related to technology or technical processes with an emphasis on short, unique words

    oai_token-act-pair · gpt-3.5-turbo

    product names and specific terms related to technology or digital media

    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
     thereto
    -0.52
     âĢ¦"
    -0.49
    20439
    -0.48
    pheus
    -0.46
     respectively
    -0.46
     thereof
    -0.45
     Frie
    -0.45
     trans
    -0.43
    zona
    -0.42
     Krug
    -0.42
    POSITIVE LOGITS
    resa
    0.80
    xiety
    0.70
    asionally
    0.69
    phabet
    0.65
    odore
    0.64
    roximately
    0.63
    anyahu
    0.63
    hesda
    0.63
    Berry
    0.61
    withstanding
    0.61
    Activations Density 0.626%

    No Known Activations