© 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. 2-RES-JB
    11. 512
    Prev
    Next
    INDEX
    Explanations

    the word "Where"

    oai_token-act-pair · gpt-4-turbo

    words related to locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wu
    -0.67
    )].
    -0.65
    astics
    -0.64
     Doctrine
    -0.61
    asts
    -0.61
    agers
    -0.61
     roller
    -0.61
    asted
    -0.60
    ³³³³³³³³
    -0.59
    yi
    -0.59
    POSITIVE LOGITS
    abouts
    1.38
    soever
    1.36
    upon
    1.30
    fore
    1.09
    ver
    0.92
    nces
    0.89
    Where
    0.82
    where
    0.82
    ĪĴ
    0.78
    iago
    0.75
    Activations Density 0.034%

    No Known Activations