© 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. 7694
    Prev
    Next
    INDEX
    Explanations

    phrases related to infestation, especially in negative contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "written" and various forms of the word "sod" in contexts related to events or actions

    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
    ifted
    -0.80
     simultane
    -0.78
    awaru
    -0.77
     cumbers
    -0.76
    ħĭ
    -0.75
    aucas
    -0.73
    bably
    -0.72
    perty
    -0.70
     surv
    -0.68
    Ļ½
    -0.68
    POSITIVE LOGITS
    mast
    0.87
    itten
    0.83
     Craw
    0.77
    yard
    0.74
    bury
    0.74
    combe
    0.72
    acht
    0.71
    bats
    0.71
    berg
    0.70
    burg
    0.69
    Activations Density 0.010%

    No Known Activations