© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 24046
    Prev
    Next
    INDEX
    Explanations

    phrases related to accepting something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to acceptance and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iery
    -0.73
    abouts
    -0.72
    akin
    -0.68
    borough
    -0.66
     Alley
    -0.66
    ixt
    -0.66
    lling
    -0.66
    enne
    -0.65
    ////////////////////////////////
    -0.64
    ginx
    -0.64
    POSITIVE LOGITS
     invitation
    1.01
     uncond
    0.96
     resignation
    0.90
     premise
    0.89
     unres
    0.87
     apology
    0.86
     invitations
    0.82
     responsibility
    0.82
     validity
    0.81
     entirety
    0.81
    Activations Density 0.225%

    No Known Activations