© 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. 16368
    Prev
    Next
    INDEX
    Explanations

    the word "else" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "anything else."

    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
    haw
    -0.70
    Lee
    -0.67
    anon
    -0.62
    uto
    -0.62
    OA
    -0.61
     heterogeneity
    -0.60
    ISSION
    -0.58
    asma
    -0.58
    ulas
    -0.58
    ASED
    -0.58
    POSITIVE LOGITS
    worldly
    1.10
     else
    0.89
    Else
    0.84
     describ
    0.83
    swer
    0.83
    else
    0.78
     destro
    0.78
     nodd
    0.74
    okia
    0.71
    where
    0.70
    Activations Density 0.017%

    No Known Activations