© 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. 5179
    Prev
    Next
    INDEX
    Explanations

    website elements related to user engagement and interaction

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated phrases or clauses used for information and updates

    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
    Ļ½
    -0.74
    oming
    -0.70
    ©
    -0.70
     antit
    -0.68
    arde
    -0.66
    untarily
    -0.66
     eminent
    -0.66
    Marginal
    -0.65
    ¬¼
    -0.64
     tert
    -0.63
    POSITIVE LOGITS
     please
    1.10
     PLEASE
    0.92
    please
    0.87
     including
    0.83
     Please
    0.80
     click
    0.80
     etc
    0.79
     albeit
    0.78
     Leban
    0.75
     however
    0.75
    Activations Density 0.348%

    No Known Activations