© 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. 9-RES-JB
    11. 20778
    Prev
    Next
    INDEX
    Explanations

    phrases related to the cause and effect relationship

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "because of"

    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
    iaries
    -0.89
    irez
    -0.83
    cember
    -0.81
    iva
    -0.78
    iac
    -0.77
    ivating
    -0.74
    ishi
    -0.73
    itone
    -0.72
    quet
    -0.70
    soever
    -0.70
    POSITIVE LOGITS
     sheer
    1.01
     fears
    0.97
     loopholes
    0.95
     lack
    0.95
     uncertainties
    0.94
     inconsistencies
    0.94
     concerns
    0.92
     complications
    0.90
     limitations
    0.90
     differences
    0.89
    Activations Density 0.076%

    No Known Activations