© 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. 13486
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenging or difficult situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant challenges or critical aspects in various contexts

    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
    */(
    -0.52
    debian
    -0.50
    Å¡
    -0.49
     cutoff
    -0.48
    offer
    -0.48
     muted
    -0.47
    idav
    -0.47
     Transcript
    -0.47
     briefed
    -0.47
     caveats
    -0.46
    POSITIVE LOGITS
     mankind
    0.70
     humankind
    0.70
    ankind
    0.69
     endeavor
    0.61
     endeavour
    0.60
     millennium
    0.58
     endeavors
    0.57
    Americ
    0.56
     humanity
    0.55
     era
    0.55
    Activations Density 1.555%

    No Known Activations