© 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. 7167
    Prev
    Next
    INDEX
    Explanations

    phrases related to compensating for losses or shortcomings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compensation or making up for something

    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
    abet
    -0.83
    prints
    -0.81
    nih
    -0.78
    ums
    -0.70
    ulhu
    -0.70
    rogens
    -0.68
    onic
    -0.65
    join
    -0.64
    wired
    -0.64
    arge
    -0.63
    POSITIVE LOGITS
     boredom
    0.78
    ById
    0.75
     losses
    0.70
     shortfall
    0.69
     disruptions
    0.68
     deficiencies
    0.68
     adversity
    0.68
     adequately
    0.67
     Irma
    0.67
     inexper
    0.65
    Activations Density 0.209%

    No Known Activations