© 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. 9589
    Prev
    Next
    INDEX
    Explanations

    locations or organizations followed by names or titles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places and organizations

    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
    liners
    -0.78
    ities
    -0.73
    ages
    -0.70
     Canaver
    -0.69
    ctors
    -0.68
    ogens
    -0.68
     Brendan
    -0.67
    rons
    -0.66
    brates
    -0.65
     Haf
    -0.65
    POSITIVE LOGITS
     staffer
    0.99
     employee
    0.86
     colleague
    0.85
     competitor
    0.77
     exclusive
    0.76
     clone
    0.75
     endorsement
    0.75
    OVA
    0.74
     representative
    0.74
     staple
    0.74
    Activations Density 0.422%

    No Known Activations