© 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. 12579
    Prev
    Next
    INDEX
    Explanations

    instances where the word "however" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "however" used in various contexts

    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
    MAL
    -0.67
    CLOSE
    -0.65
    SourceFile
    -0.63
    /
    -0.62
    Next
    -0.60
    mates
    -0.60
     (>
    -0.59
    RAL
    -0.58
    NECT
    -0.58
    mate
    -0.57
    POSITIVE LOGITS
    has
    0.72
     seems
    0.68
     concedes
    0.66
     ignores
    0.65
     isn
    0.65
     begs
    0.64
     according
    0.63
     acknowledges
    0.63
     wasn
    0.63
     unlike
    0.63
    Activations Density 0.122%

    No Known Activations