© 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 EvalsExportsAPI 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. 3930
    Prev
    Next
    INDEX
    Explanations

    phrases referring to significant or impactful moments

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or impactful moments

    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
    ply
    -0.82
    uct
    -0.81
    pel
    -0.76
    achev
    -0.74
    yu
    -0.74
    raid
    -0.73
    vacc
    -0.71
    yss
    -0.71
    GE
    -0.71
    abet
    -0.70
    POSITIVE LOGITS
     moments
    1.26
     Moments
    1.18
    hift
    0.99
    aneously
    0.96
     moment
    0.92
     Minutes
    0.87
     lapse
    0.85
     milestones
    0.82
     Moment
    0.81
    aneous
    0.79
    Activations Density 0.020%

    No Known Activations