© 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. 6896
    Prev
    Next
    INDEX
    Explanations

    references to the prevalence of certain phenomena or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prevalence and incidence of various phenomena or conditions

    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
    ebus
    -0.82
    adelphia
    -0.82
    paio
    -0.76
    izons
    -0.70
    imov
    -0.68
    letes
    -0.68
     externalToEVAOnly
    -0.67
    bies
    -0.67
    zyk
    -0.66
    idges
    -0.66
    POSITIVE LOGITS
     preval
    1.07
     prevalence
    1.00
     prevalent
    0.88
     incidence
    0.74
    ulhu
    0.72
    Û
    0.71
     Outbreak
    0.69
     Trend
    0.69
    entimes
    0.68
    wealth
    0.68
    Activations Density 0.016%

    No Known Activations