© 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. 3-RES-JB
    11. 1840
    Prev
    Next
    INDEX
    Explanations

    instances of the word "somehow"

    oai_token-act-pair · gpt-3.5-turbo

    the word "somehow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agents
    -0.76
    oft
    -0.67
    holder
    -0.66
    helm
    -0.66
    emies
    -0.65
     Ferr
    -0.63
     stances
    -0.62
     headers
    -0.62
    winner
    -0.60
    ioch
    -0.60
    POSITIVE LOGITS
     somew
    1.01
    Else
    0.83
     somehow
    0.82
     magically
    0.82
     managed
    0.79
    ãĤ´ãĥ³
    0.77
     mirac
    0.75
    kered
    0.71
    oping
    0.71
     overpower
    0.70
    Activations Density 0.011%

    No Known Activations