© 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. 7-RES-JB
    11. 23849
    Prev
    Next
    INDEX
    Explanations

    personal interactions related to acceptance or approval

    oai_token-act-pair · gpt-3.5-turbo

    references to accepting or receiving various types of offers, apologies, and invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ixt
    -0.75
    abouts
    -0.74
    alsh
    -0.69
    iery
    -0.69
    enne
    -0.68
    ginx
    -0.67
     Alley
    -0.67
    akin
    -0.66
    ubric
    -0.66
    acco
    -0.65
    POSITIVE LOGITS
     invitation
    1.01
     uncond
    0.89
     premise
    0.84
     gladly
    0.84
     resignation
    0.81
     invitations
    0.81
     validity
    0.81
     unres
    0.80
     responsibility
    0.75
    SpaceEngineers
    0.75
    Activations Density 0.216%

    No Known Activations