© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20677
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving up or missing out on something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating resignation or acceptance of missed opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.80
    ults
    -0.70
    UTC
    -0.70
     teasp
    -0.68
    âĵĺ
    -0.68
    utenberg
    -0.65
    reference
    -0.64
    SCP
    -0.64
     msec
    -0.63
    ãĥ¼ãĤ¯
    -0.63
    POSITIVE LOGITS
    erous
    1.11
     behalf
    1.11
     impulse
    0.82
    etime
    0.81
    eness
    0.75
    yx
    0.74
     adrenaline
    0.74
     unsuspecting
    0.73
     individuality
    0.73
     eBay
    0.72
    Activations Density 0.124%

    No Known Activations