© 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. 2-RES-JB
    11. 21739
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistical analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical analysis and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -1.09
    shire
    -0.90
    nen
    -0.84
    eem
    -0.84
    alin
    -0.81
    ding
    -0.81
    aline
    -0.76
    ijing
    -0.74
    cot
    -0.73
    minent
    -0.73
    POSITIVE LOGITS
    istically
    1.13
    istical
    1.04
     anomalies
    1.01
     anomaly
    0.98
     statistical
    0.96
     impossibility
    0.92
     illiter
    0.86
     outl
    0.84
     significance
    0.84
     statistic
    0.83
    Activations Density 0.014%

    No Known Activations