© 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. 17518
    Prev
    Next
    INDEX
    Explanations

    endorsement-related phrases or statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "endorsement."

    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
    rooms
    -0.73
    arters
    -0.73
     Smithsonian
    -0.71
    auld
    -0.71
    isen
    -0.69
    gm
    -0.69
    Crew
    -0.68
    ester
    -0.66
     Ler
    -0.66
    uscript
    -0.65
    POSITIVE LOGITS
     endorsement
    1.44
     endorsements
    1.43
     endors
    1.09
     endorsing
    1.06
     endorse
    1.05
     endorsed
    0.96
    orship
    0.89
     loyalty
    0.85
    eering
    0.84
     recommendation
    0.78
    Activations Density 0.012%

    No Known Activations