© 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. 8-RES-JB
    11. 7808
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the difficulty or impossibility of a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "difficult for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    querque
    -0.68
     withd
    -0.63
    Ü
    -0.62
     Accessed
    -0.62
    bda
    -0.62
    975
    -0.62
    jab
    -0.62
    Introduced
    -0.61
    acebook
    -0.61
    forward
    -0.60
    POSITIVE LOGITS
     us
    1.04
     anyone
    1.01
     them
    0.99
     someone
    0.98
    bidden
    0.95
     me
    0.94
    geries
    0.91
     anybody
    0.89
     him
    0.87
     employers
    0.87
    Activations Density 0.139%

    No Known Activations