© 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. 7-RES-JB
    6. 12422
    Prev
    Next
    INDEX
    Explanations

    terms related to water desalination and specific names

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "desperate" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compton
    -0.64
     nerv
    -0.62
     offense
    -0.62
     immature
    -0.60
    yip
    -0.60
     smack
    -0.58
     hypers
    -0.57
     HELL
    -0.56
    mouth
    -0.56
     Titus
    -0.56
    POSITIVE LOGITS
    ãĥīãĥ©
    0.80
    ember
    0.79
    ction
    0.78
    dule
    0.78
    ption
    0.76
    aign
    0.76
    igue
    0.74
    itte
    0.72
    mination
    0.72
    ruct
    0.70
    Activations Density 0.043%

    No Known Activations