© 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 EvalsExportsAPI 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. 14143
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Trans" followed by a number (e.g., Trans 9)

    oai_token-act-pair · gpt-3.5-turbo

    references to the Trans-Pacific Partnership and related agreements

    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
    RANT
    -0.75
    âķIJâķIJ
    -0.73
    ARD
    -0.71
     Sunder
    -0.71
    ARDS
    -0.70
    éĹĺ
    -0.70
    steen
    -0.69
    ELL
    -0.69
    pload
    -0.68
    vre
    -0.67
    POSITIVE LOGITS
    cend
    1.03
    gender
    0.98
    lator
    0.94
    continental
    0.87
    ference
    0.85
    racial
    0.84
    sexual
    0.84
    mitt
    0.84
    missible
    0.83
    porter
    0.82
    Activations Density 0.010%

    No Known Activations