© 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. 0-RES-JB
    11. 2334
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition or resistance

    oai_token-act-pair · gpt-3.5-turbo

    the term "anti" in various contexts, indicating opposition or resistance to different concepts or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    halla
    -0.82
    ername
    -0.82
    ÄŁ
    -0.79
    Done
    -0.73
     Canter
    -0.73
    yards
    -0.72
     grate
    -0.72
    estamp
    -0.72
     Cind
    -0.72
    mere
    -0.71
    POSITIVE LOGITS
     anti
    3.32
    Anti
    2.78
     Anti
    2.76
    anti
    2.31
     antit
    1.95
     antip
    1.93
     ant
    1.87
     antic
    1.86
     antid
    1.83
     antib
    1.81
    Activations Density 0.027%

    No Known Activations