© 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. 6-RES-JB
    11. 14451
    Prev
    Next
    INDEX
    Explanations

    phrases related to "poaching" or illegal hunting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "po," which often relates to various contexts involving potential harm or illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owship
    -0.83
    hips
    -0.78
    AGE
    -0.74
    AGES
    -0.73
     Mellon
    -0.71
    ELF
    -0.70
    ãĥ¯ãĥ³
    -0.69
    IELD
    -0.68
    DEV
    -0.67
    NESS
    -0.66
    POSITIVE LOGITS
    achers
    1.01
    otics
    0.98
    itives
    0.94
    inently
    0.94
    etary
    0.92
    onte
    0.90
    ached
    0.89
    urb
    0.88
    pper
    0.88
    aching
    0.87
    Activations Density 0.018%

    No Known Activations