© 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. 3-RES-JB
    11. 12300
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or entities with the abbreviation "AMF"

    oai_token-act-pair · gpt-3.5-turbo

    labels or acronyms related to organizations and agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttes
    -0.85
     Wick
    -0.75
    keye
    -0.73
    keyes
    -0.68
    accompanied
    -0.67
    ãĥ¼ãĥ«
    -0.65
     externalToEVAOnly
    -0.65
    kson
    -0.65
     Strait
    -0.64
     Directions
    -0.64
    POSITIVE LOGITS
    ICAN
    1.33
    endment
    1.08
    AZ
    1.07
    MY
    1.07
    sterdam
    1.05
    URA
    1.03
    OTO
    1.01
    AM
    1.00
    PLIC
    0.98
    ARC
    0.97
    Activations Density 0.009%

    No Known Activations