© 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. 2-RES-JB
    11. 360
    Prev
    Next
    INDEX
    Explanations

    the word "obtain" or its variations

    oai_token-act-pair · gpt-4-turbo

    words related to obtaining, acquiring, or receiving something

    oai_token-act-pair · gpt-3.5-turbo

    words related to acquiring or retrieving information or items

    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
    cas
    -0.82
    heartedly
    -0.72
    psc
    -0.70
    timer
    -0.65
     Wells
    -0.62
     Britann
    -0.61
    gaard
    -0.61
    dry
    -0.60
    hov
    -0.60
     sterling
    -0.60
    POSITIVE LOGITS
    itures
    0.83
     access
    0.82
    tains
    0.81
    CLASSIFIED
    0.81
    eteenth
    0.79
     obtain
    0.78
    andom
    0.77
     obtained
    0.76
    Materials
    0.75
    rarily
    0.72
    Activations Density 0.019%

    No Known Activations