© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5168
    Prev
    Next
    INDEX
    Explanations

    references to locations or places, specifically as "homes" of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a place that is considered a "home" or residence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undo
    -0.76
    andum
    -0.73
    imester
    -0.71
    uel
    -0.69
     Delta
    -0.68
    ifter
    -0.66
    asm
    -0.65
    estamp
    -0.65
    ongyang
    -0.64
    veyard
    -0.64
    POSITIVE LOGITS
    coming
    0.93
    grown
    0.90
    nikov
    0.87
    opathy
    0.85
    opathic
    0.82
    itiz
    0.80
    pun
    0.80
    quartered
    0.77
    brew
    0.77
    )=(
    0.74
    Activations Density 0.030%

    No Known Activations