© 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. 6-RES-JB
    6. 15246
    Prev
    Next
    INDEX
    Explanations

    Although statements conveying a contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "albeit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogy
    -0.74
    McC
    -0.74
    aku
    -0.72
    oshenko
    -0.71
    asus
    -0.71
    rush
    -0.70
    iew
    -0.70
    ursday
    -0.69
    orters
    -0.68
    rup
    -0.67
    POSITIVE LOGITS
    chery
    0.93
     fortunately
    0.84
     marginally
    0.83
     unintentional
    0.80
     unsuccessfully
    0.79
     briefly
    0.79
     admittedly
    0.79
     modest
    0.78
     curiously
    0.78
    withstanding
    0.78
    Activations Density 0.021%

    No Known Activations