© 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. 5182
    Prev
    Next
    INDEX
    Explanations

    prepositions that indicate location or time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate frequency or timing of actions

    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
     Hess
    -0.66
     Kafka
    -0.61
    ãģĻ
    -0.61
     Owens
    -0.60
     Sands
    -0.59
    oresc
    -0.58
     Sparrow
    -0.57
     asylum
    -0.57
    ARD
    -0.57
     Gamble
    -0.57
    POSITIVE LOGITS
    pires
    1.20
    ifies
    0.99
    pired
    0.86
    itially
    0.83
    ked
    0.78
    stood
    0.76
    ÃĥÃĤ
    0.76
    ted
    0.75
    handled
    0.73
    played
    0.72
    Activations Density 0.575%

    No Known Activations