© 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. 7-RES-JB
    11. 21181
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations, statistics, and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.66
    ģ«
    -0.64
    apor
    -0.61
    cular
    -0.61
    andowski
    -0.60
     sqor
    -0.60
    utenberg
    -0.59
    oola
    -0.58
    ysis
    -0.58
     pregn
    -0.57
    POSITIVE LOGITS
     Gaul
    0.62
    oak
    0.59
     Romans
    0.58
    veland
    0.56
     mainline
    0.55
    Atl
    0.54
     sand
    0.54
     Maced
    0.53
    mont
    0.51
    Benz
    0.51
    Activations Density 0.643%

    No Known Activations