© 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. 23105
    Prev
    Next
    INDEX
    Explanations

    words related to military operations and ranks

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "us" 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
    ournals
    -0.81
    tags
    -0.81
    rush
    -0.72
    ARK
    -0.72
    sheet
    -0.72
    parser
    -0.69
    atcher
    -0.69
    ingham
    -0.69
    owsky
    -0.68
    ACK
    -0.68
    POSITIVE LOGITS
     Mons
    0.79
     Gentleman
    0.75
     fide
    0.75
     lett
    0.72
     la
    0.72
     dilig
    0.71
     Claud
    0.70
     Vict
    0.69
     dé
    0.69
     Rouge
    0.68
    Activations Density 0.291%

    No Known Activations