© 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. 11-RES-JB
    11. 5276
    Prev
    Next
    INDEX
    Explanations

    sentences indicating the outcome or consequence of a given situation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aths
    -0.89
    aughtered
    -0.83
    aughed
    -0.81
    ickets
    -0.78
    acers
    -0.78
    tones
    -0.73
    ARS
    -0.72
     Shots
    -0.71
    aneers
    -0.71
    adle
    -0.71
    POSITIVE LOGITS
     includes
    1.22
     phenomenon
    1.18
     applies
    1.17
     implies
    1.15
     begs
    1.13
     tendency
    1.11
     translates
    1.11
     explains
    1.10
     imbalance
    1.09
     manifests
    1.08
    Activations Density 0.135%

    No Known Activations