© 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. 11-RES-JB
    11. 5221
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving something a try or a chance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.67
    velt
    -0.65
    iche
    -0.65
    nown
    -0.61
    iffe
    -0.60
    ropolitan
    -0.59
    alde
    -0.58
    è¦
    -0.57
    sure
    -0.56
    ired
    -0.56
    POSITIVE LOGITS
     away
    1.08
     precedence
    0.95
     priority
    0.88
     Away
    0.86
     props
    0.83
     thumbs
    0.77
     another
    0.76
     CPR
    0.74
     legitimacy
    0.73
     permission
    0.72
    Activations Density 0.085%

    No Known Activations