© 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. 11-RES-JB
    11. 14878
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations where events occur, particularly homes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "home" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andum
    -0.78
    uality
    -0.71
     Delta
    -0.62
    asm
    -0.61
     riders
    -0.61
     rider
    -0.61
    UMP
    -0.60
     Stras
    -0.59
     Samson
    -0.59
     sshd
    -0.58
    POSITIVE LOGITS
    coming
    1.20
    pun
    1.19
    chool
    1.18
    opathic
    1.11
    comings
    1.02
    builder
    0.96
    owner
    0.95
    wife
    0.93
    owners
    0.93
    ported
    0.93
    Activations Density 0.050%

    No Known Activations