© 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. 12141
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need to address or handle issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of managing or handling difficult situations

    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
    OGR
    -0.84
    owed
    -0.74
    chart
    -0.73
    owitz
    -0.65
    STAT
    -0.64
    ischer
    -0.63
    orah
    -0.63
     Guilty
    -0.63
    falls
    -0.63
    handler
    -0.63
    POSITIVE LOGITS
     adversity
    0.87
     pesky
    0.71
    stood
    0.69
     issues
    0.69
     Deity
    0.66
     them
    0.65
     regard
    0.65
    =-=-=-=-
    0.62
     grievances
    0.62
     exotic
    0.61
    Activations Density 0.057%

    No Known Activations