© 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. 8-RES-JB
    11. 7853
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the difficulty or challenge of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rongh
    -0.77
    roma
    -0.68
    aura
    -0.61
    ship
    -0.60
    irie
    -0.59
    depend
    -0.58
    bey
    -0.57
    threat
    -0.57
    gemony
    -0.57
    Kings
    -0.57
    POSITIVE LOGITS
     enough
    1.02
     consolation
    0.79
     imagining
    0.72
     circumst
    0.71
     coincidence
    0.71
    entimes
    0.70
     underest
    0.69
     understatement
    0.68
     exaggeration
    0.67
     vain
    0.66
    Activations Density 0.055%

    No Known Activations