© 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 EvalsExportsinterp-engineNEWAPI 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. 998
    Prev
    Next
    INDEX
    Explanations

    negative emotions and situations such as struggling, hating, feeling horrible, and being sentenced

    oai_token-act-pair · gpt-3.5-turbo

    instances of emotional distress or struggle

    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
    UF
    -0.69
    raft
    -0.69
    ourse
    -0.68
    SpaceEngineers
    -0.65
    cott
    -0.64
     concess
    -0.63
    urrent
    -0.63
    conom
    -0.63
    Claim
    -0.63
    asury
    -0.62
    POSITIVE LOGITS
     huh
    1.17
     haha
    1.11
     yeah
    1.02
     but
    1.00
     eh
    0.99
     oh
    0.96
     albeit
    0.93
     though
    0.92
     blah
    0.91
     maybe
    0.88
    Activations Density 0.535%

    No Known Activations