© 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. 3-RES-JB
    11. 17979
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that are unfolding or occurring

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "goes" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shaw
    -0.73
    tone
    -0.69
    gh
    -0.66
    rone
    -0.65
    ples
    -0.65
    cos
    -0.65
    owers
    -0.65
    conn
    -0.64
    inion
    -0.64
    stad
    -0.63
    POSITIVE LOGITS
    ometimes
    1.16
    omething
    1.09
    ilver
    1.02
    terday
    0.94
    ynthesis
    0.90
    pace
    0.89
    hift
    0.87
    paces
    0.86
    everal
    0.81
    ettings
    0.79
    Activations Density 0.159%

    No Known Activations