© 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. 4-RES-JB
    11. 2401
    Prev
    Next
    INDEX
    Explanations

    references to news agencies or media outlets, particularly recognizing mentions of "CNN."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the news outlet CNN

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

    No Comments

    Negative Logits
    bers
    -0.68
    scope
    -0.67
    sed
    -0.67
    brow
    -0.65
     Neck
    -0.64
    wear
    -0.63
     '.
    -0.63
    case
    -0.62
     Fifa
    -0.61
    team
    -0.60
    POSITIVE LOGITS
    )—
    1.00
    CBC
    0.98
    )--
    0.96
    +)
    0.86
    )"
    0.85
    )
    0.84
    CW
    0.81
    -)
    0.81
    ):
    0.79
    ),"
    0.78
    Activations Density 0.033%

    No Known Activations