© 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. 13016
    Prev
    Next
    INDEX
    Explanations

    commands or requests instructing someone to share personal information or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that prompt for personal information or experiences

    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
     ILCS
    -0.77
    urdue
    -0.75
    perty
    -0.74
    erala
    -0.69
    ó
    -0.68
    engeance
    -0.68
    hered
    -0.63
    emetery
    -0.63
    cdn
    -0.63
    hate
    -0.63
    POSITIVE LOGITS
    tale
    1.50
    ingly
    1.21
    tell
    1.13
     Tell
    1.05
    ings
    0.86
     tell
    0.84
    Tell
    0.83
     me
    0.83
    biz
    0.81
     us
    0.80
    Activations Density 0.018%

    No Known Activations