© 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. 2-RES-JB
    11. 20867
    Prev
    Next
    INDEX
    Explanations

    proper names or unique identifiers, possibly related to media production or politics

    oai_token-act-pair · gpt-3.5-turbo

    the word "sten" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PLAN
    -0.70
     NCT
    -0.67
    WD
    -0.64
    IRD
    -0.63
     incidentally
    -0.63
     totality
    -0.61
     Debor
    -0.60
     Northeast
    -0.59
     mileage
    -0.59
     AQ
    -0.58
    POSITIVE LOGITS
    sten
    1.66
    cil
    1.14
    burgh
    0.95
    opsis
    0.84
     Herz
    0.84
    zen
    0.81
    ium
    0.81
    ffen
    0.81
    âĸ¬âĸ¬
    0.78
    oscopic
    0.77
    Activations Density 0.006%

    No Known Activations