© 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. 9-RES-JB
    11. 18458
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to military, political figures, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "General" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ologies
    -0.81
    gypt
    -0.76
    dogs
    -0.70
    ï¸
    -0.69
    bley
    -0.68
    ILLE
    -0.67
    ngth
    -0.63
    vable
    -0.63
    gp
    -0.61
    ħĭ
    -0.61
    POSITIVE LOGITS
    izations
    1.00
     Motors
    0.97
     Electric
    0.92
     Dynamics
    0.90
    ization
    0.87
    isations
    0.85
    isation
    0.85
     Purpose
    0.83
     Election
    0.80
     Assembly
    0.80
    Activations Density 0.022%

    No Known Activations