© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20024
    Prev
    Next
    INDEX
    Explanations

    references to living quarters or dwellings

    oai_token-act-pair · gpt-3.5-turbo

    references to living spaces or accommodations

    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
     Rudd
    -0.67
     Rosenberg
    -0.67
     HERO
    -0.66
    isner
    -0.65
    Reviewed
    -0.64
    NetMessage
    -0.63
    IK
    -0.60
    gee
    -0.60
    UL
    -0.59
     Proposition
    -0.59
    POSITIVE LOGITS
     quarters
    1.25
    quarters
    1.04
    pring
    1.02
    een
    0.92
    hare
    0.90
    eteen
    0.85
    quarter
    0.83
    uits
    0.81
    chool
    0.80
    pite
    0.77
    Activations Density 0.009%

    No Known Activations