© 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. 9475
    Prev
    Next
    INDEX
    Explanations

    locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    sentences that describe the status or characteristics of objects or events

    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
    uld
    -0.67
    dies
    -0.65
    ue
    -0.62
     parties
    -0.61
     selves
    -0.61
    rities
    -0.61
    aths
    -0.61
     Spirits
    -0.60
    sheet
    -0.58
    mosp
    -0.58
    POSITIVE LOGITS
     sorely
    0.79
     tremendously
    0.78
     extremely
    0.76
     extraordinarily
    0.76
     blat
    0.75
     awfully
    0.75
     definitely
    0.75
     immensely
    0.74
     greatly
    0.74
     strikingly
    0.74
    Activations Density 0.339%

    No Known Activations