© 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. 11592
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking advantage of opportunities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest taking advantage of opportunities or resources

    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
    heres
    -0.72
    eller
    -0.68
     magnets
    -0.68
    etheless
    -0.67
    ili
    -0.66
     apes
    -0.64
    bia
    -0.62
     coasts
    -0.61
     withholding
    -0.61
     brace
    -0.60
    POSITIVE LOGITS
    Parameter
    0.76
    kef
    0.71
    Lenin
    0.69
    erto
    0.69
    */(
    0.67
    ãĥīãĥ©
    0.67
    igious
    0.66
     Sind
    0.65
    fecture
    0.65
    fect
    0.63
    Activations Density 0.353%

    No Known Activations