© 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. 9-RES-JB
    11. 4103
    Prev
    Next
    INDEX
    Explanations

    *Contradictions* or *unexpected outcomes* in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "even though."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vantage
    -0.83
    IGN
    -0.71
    eed
    -0.70
     pione
    -0.68
    utical
    -0.67
    OE
    -0.67
    ilan
    -0.66
    idency
    -0.66
    isively
    -0.66
    oeuv
    -0.65
    POSITIVE LOGITS
     they
    0.92
     technically
    0.87
     it
    0.81
     admitting
    0.79
     he
    0.77
     there
    0.74
     we
    0.73
     acknowledging
    0.71
     she
    0.70
     millions
    0.70
    Activations Density 0.076%

    No Known Activations