© 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. 9941
    Prev
    Next
    INDEX
    Explanations

    locations or unspecified places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anywhere" indicating varied locations or contexts

    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
    apo
    -0.75
    asting
    -0.72
    bal
    -0.72
    seless
    -0.68
    asts
    -0.68
    roma
    -0.67
    ulously
    -0.66
    othy
    -0.66
    pu
    -0.66
    quel
    -0.65
    POSITIVE LOGITS
     else
    1.43
    abouts
    1.17
    Else
    1.13
     Else
    1.12
     imaginable
    0.94
    else
    0.90
    where
    0.82
    ĪĴ
    0.76
    ħĭ
    0.75
     conceivable
    0.71
    Activations Density 0.015%

    No Known Activations