© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 22635
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speculation or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express skepticism or questioning assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Azerb
    -0.68
     Hung
    -0.65
     Ramos
    -0.60
     Irma
    -0.59
     Avatar
    -0.59
    igators
    -0.59
     Jiu
    -0.59
     Redmond
    -0.58
     Reloaded
    -0.58
     FSA
    -0.58
    POSITIVE LOGITS
    depending
    0.93
     guiIcon
    0.92
    peat
    0.88
     versa
    0.87
     thereof
    0.83
    Else
    0.81
    abouts
    0.80
    ught
    0.77
    else
    0.75
     guiActiveUn
    0.75
    Activations Density 0.763%

    No Known Activations