© 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. 9-RES-JB
    11. 8877
    Prev
    Next
    INDEX
    Explanations

    words related to contrasting viewpoints or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest unwavering determination or commitment to a cause

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leban
    -0.56
    vertisement
    -0.56
    ainment
    -0.56
    luster
    -0.55
    AMI
    -0.54
    igree
    -0.52
    ornings
    -0.52
    rition
    -0.51
    ogether
    -0.50
    accompan
    -0.50
    POSITIVE LOGITS
     Allaah
    0.71
    Jews
    0.69
     Jews
    0.68
     doesnt
    0.66
    nt
    0.65
     anarchists
    0.63
    humans
    0.60
     cunt
    0.60
     fuck
    0.59
     atheists
    0.59
    Activations Density 0.954%

    No Known Activations