© 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. 22987
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations with the abbreviation "LA"

    oai_token-act-pair · gpt-3.5-turbo

    references to Los Angeles

    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
    mind
    -0.79
    ens
    -0.74
    orius
    -0.73
    maps
    -0.73
    rice
    -0.71
    space
    -0.70
    ensible
    -0.70
    lins
    -0.70
    re
    -0.69
    mos
    -0.69
    POSITIVE LOGITS
    BILITY
    1.23
    BIL
    1.18
    BILITIES
    1.07
    ISM
    1.03
    UGH
    1.01
    ZE
    1.01
    uthor
    1.01
    ULTS
    0.96
    velength
    0.96
    ULT
    0.95
    Activations Density 0.024%

    No Known Activations