© 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. 12594
    Prev
    Next
    INDEX
    Explanations

    phrases related to following instructions or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "follow."

    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
    pite
    -0.83
    inese
    -0.66
    unicip
    -0.65
     ILCS
    -0.65
    rimination
    -0.64
    ldom
    -0.64
    ukemia
    -0.62
    negie
    -0.62
    orc
    -0.62
     wounding
    -0.62
    POSITIVE LOGITS
    follow
    0.86
     Follow
    0.78
     follow
    0.77
     follows
    0.75
     closely
    0.73
    ĸļ
    0.72
     suit
    0.72
    LLOW
    0.71
    SHIP
    0.69
    ansen
    0.68
    Activations Density 0.034%

    No Known Activations