© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16527
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficulty or challenging situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing difficulty or the challenge of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rongh
    -0.70
    irie
    -0.65
    anded
    -0.59
    Kings
    -0.57
    gdala
    -0.56
    rones
    -0.55
    gemony
    -0.55
    @#&
    -0.55
    inances
    -0.54
    oak
    -0.53
    POSITIVE LOGITS
     enough
    0.93
     to
    0.83
     imagining
    0.82
    coded
    0.81
    wired
    0.76
     consolation
    0.72
     underest
    0.68
     imagine
    0.65
     knowing
    0.65
     convincing
    0.65
    Activations Density 0.053%

    No Known Activations