© 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. 4-RES-JB
    11. 12339
    Prev
    Next
    INDEX
    Explanations

    keywords related to the action of lodging or staying somewhere

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accommodation or staying places

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

    No Comments

    Negative Logits
    enegger
    -0.74
     Mub
    -0.71
    rawdownloadcloneembedreportprint
    -0.71
    schild
    -0.71
    =-=-=-=-=-=-=-=-
    -0.68
    onson
    -0.67
    ymm
    -0.65
     Morg
    -0.64
    ONSORED
    -0.64
     Saul
    -0.63
    POSITIVE LOGITS
    pole
    1.30
    itory
    0.98
     lodge
    0.96
    mate
    0.92
    holder
    0.91
    holders
    0.86
    nery
    0.83
    mates
    0.82
    estone
    0.81
     lodged
    0.81
    Activations Density 0.010%

    No Known Activations