© 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. 2-RES-JB
    6. 14069
    Prev
    Next
    INDEX
    Explanations

    words related to professions, particularly those ending in "-er" or "-der"

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "enders" and "ers" associated with specific roles or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Territories
    -0.68
     Cooperation
    -0.61
    ige
    -0.59
     bilateral
    -0.58
     Byrne
    -0.57
     Reconstruction
    -0.57
    plane
    -0.56
    560
    -0.56
     Border
    -0.56
    nce
    -0.56
    POSITIVE LOGITS
    poons
    1.34
    paces
    1.30
    mith
    1.29
    hip
    1.22
    uggest
    1.17
    ervatives
    1.16
    poon
    1.13
    pace
    1.10
    ucker
    1.08
    ervative
    1.03
    Activations Density 0.059%

    No Known Activations