© 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. 13800
    Prev
    Next
    INDEX
    Explanations

    words ending in '-ally'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that suggest a collective or shared action

    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
    href
    -0.76
     Pirate
    -0.71
     Riders
    -0.66
     Settlement
    -0.65
     Bengals
    -0.63
     Notting
    -0.63
     Franks
    -0.63
     Julio
    -0.63
     Commissioners
    -0.63
     Vikings
    -0.62
    POSITIVE LOGITS
     minded
    0.81
     speaking
    0.76
    icious
    0.73
    mph
    0.71
    ized
    0.70
    izing
    0.69
    APH
    0.69
    UNCH
    0.69
    ize
    0.69
    izes
    0.69
    Activations Density 0.018%

    No Known Activations