© 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. 9-RES-JB
    11. 17515
    Prev
    Next
    INDEX
    Explanations

    phrases related to unwillingness or inability to do something

    oai_token-act-pair · gpt-3.5-turbo

    coordinating conjunctions and expressions of willingness or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neau
    -0.77
     Gleaming
    -0.75
     Heads
    -0.73
    eteenth
    -0.66
    CRIP
    -0.65
     Dian
    -0.64
    Winged
    -0.63
    Enlarge
    -0.63
    iHUD
    -0.62
     Diver
    -0.62
    POSITIVE LOGITS
     obligation
    0.91
     willing
    0.88
     necessity
    0.87
     advisable
    0.85
     barg
    0.85
     desire
    0.85
     unwilling
    0.84
     eager
    0.83
     probable
    0.83
     desired
    0.81
    Activations Density 0.180%

    No Known Activations