© 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. 21128
    Prev
    Next
    INDEX
    Explanations

    words related to options or choices

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" in contexts involving choices or alternatives

    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
    ires
    -0.75
    poke
    -0.74
    erest
    -0.70
    IDENT
    -0.69
    jar
    -0.68
    lights
    -0.68
    IGHTS
    -0.67
    ETS
    -0.66
    emi
    -0.66
    ender
    -0.64
    POSITIVE LOGITS
    chard
    1.01
     whatever
    0.94
     alternatively
    0.92
    nery
    0.91
    Else
    0.90
    chid
    0.87
     perhaps
    0.85
    acle
    0.85
    ifice
    0.84
     even
    0.82
    Activations Density 0.101%

    No Known Activations