© 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. 2150
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to specific countries or places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ica," indicating a focus on specific terms or names relating to topics in science, geography, or cultural references

    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
    sworth
    -0.88
    legged
    -0.81
    INGTON
    -0.80
    down
    -0.79
    stroke
    -0.72
    downs
    -0.72
    irection
    -0.71
    mable
    -0.71
    lessly
    -0.71
    ty
    -0.69
    POSITIVE LOGITS
    emia
    0.94
     Rica
    0.89
     Reborn
    0.85
    zzo
    0.83
    ption
    0.77
    ppa
    0.76
     Juda
    0.75
    utical
    0.75
     Scotia
    0.75
    ahu
    0.75
    Activations Density 0.043%

    No Known Activations