© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 11059
    Prev
    Next
    INDEX
    Explanations

    terms related to statistics or data analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistics and statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.81
    aline
    -0.80
    Interstitial
    -0.69
    ModLoader
    -0.69
    eem
    -0.68
     Continental
    -0.68
    ergy
    -0.67
    WithNo
    -0.66
     Huck
    -0.65
    uran
    -0.65
    POSITIVE LOGITS
    istical
    0.92
    istics
    0.86
     analytics
    0.84
    Statistics
    0.81
    iologist
    0.80
    iology
    0.77
    istically
    0.76
     visualization
    0.75
     literacy
    0.74
    iological
    0.72
    Activations Density 0.051%

    No Known Activations