© 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. 15494
    Prev
    Next
    INDEX
    Explanations

    entities or topics related to controversy or competition

    oai_token-act-pair · gpt-3.5-turbo

    words related to "continuation" or ongoing processes

    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
    EStream
    -0.98
    terday
    -0.83
    lihood
    -0.77
    nown
    -0.75
    manship
    -0.75
    gow
    -0.72
    anwhile
    -0.72
    ãĤ¬
    -0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    ħĭ
    -0.68
    POSITIVE LOGITS
    ainers
    1.13
    ributed
    1.10
    roversial
    1.09
    ainment
    1.09
    rovers
    1.08
    ribute
    1.08
    ribution
    1.04
    ents
    1.02
    acts
    1.01
    izoph
    0.98
    Activations Density 0.008%

    No Known Activations