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

    Neuronpedia

    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. 9103
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Hager"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual with the surname "Hager"

    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
    paying
    -0.61
     cumbers
    -0.59
     Reincarn
    -0.58
     segregated
    -0.58
     stocking
    -0.58
    spread
    -0.58
    posted
    -0.57
    violence
    -0.57
    ĪĴ
    -0.56
    eco
    -0.56
    POSITIVE LOGITS
    TAIN
    1.04
    strom
    0.97
    ager
    0.96
    opol
    0.85
    ries
    0.79
    jee
    0.78
    owitz
    0.78
    stown
    0.75
    deen
    0.75
    ry
    0.74
    Activations Density 0.009%

    No Known Activations