© 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. 5188
    Prev
    Next
    INDEX
    Explanations

    instances involving specific names or numeric identifiers with additional context provided

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations associated with the United Nations or its officials

    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
     ingred
    -0.74
     Dickinson
    -0.71
    DragonMagazine
    -0.70
    tenance
    -0.70
     Extras
    -0.65
    ãĤ¤ãĥĪ
    -0.65
    imore
    -0.65
     ILCS
    -0.63
    ktop
    -0.62
     Flavoring
    -0.62
    POSITIVE LOGITS
    direction
    1.00
    nom
    0.94
    gee
    0.92
    Ma
    0.90
    chan
    0.90
    Fi
    0.88
    shaped
    0.88
    talk
    0.85
    fi
    0.84
    La
    0.84
    Activations Density 0.075%

    No Known Activations