© 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. 10-RES-JB
    11. 8140
    Prev
    Next
    INDEX
    Explanations

    instances where an action is attempted but met with resistance or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    the word "but" along with contexts implying struggle or failure

    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
    ocative
    -0.86
    代
    -0.71
    MN
    -0.69
    farious
    -0.69
    è¦ļéĨĴ
    -0.67
    icate
    -0.66
    aez
    -0.65
    igate
    -0.65
    mable
    -0.63
    solid
    -0.63
    POSITIVE LOGITS
     couldn
    1.27
     alas
    1.27
     refused
    1.20
     lacked
    1.19
     withdrew
    1.19
     hesitated
    1.13
     forgot
    1.12
     failed
    1.08
     succumbed
    1.08
     unfortunately
    1.06
    Activations Density 0.105%

    No Known Activations