© 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. 22995
    Prev
    Next
    INDEX
    Explanations

    words related to authority and commands

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize key insights or revelations

    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
    Tokens
    -0.51
    lambda
    -0.49
    FFFF
    -0.49
    ãĥ¼ãĥĨ
    -0.47
    chuk
    -0.47
    ]+
    -0.46
    emale
    -0.46
     indistinguishable
    -0.45
    æµ
    -0.45
    ãĥĩãĤ£
    -0.45
    POSITIVE LOGITS
     Background
    0.52
     largeDownload
    0.50
     GOODMAN
    0.47
     Dism
    0.47
    reb
    0.46
    resa
    0.45
     PRESS
    0.45
     DRAGON
    0.45
    ccording
    0.44
     DARK
    0.43
    Activations Density 2.169%

    No Known Activations