© 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. 11-RES-JB
    11. 10290
    Prev
    Next
    INDEX
    Explanations

    instances of the word "somehow"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "somehow" and related phrases indicating uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spect
    -0.73
    vation
    -0.71
    tnc
    -0.69
    uties
    -0.67
    ourse
    -0.67
    emies
    -0.67
    rament
    -0.66
    OTOS
    -0.66
    markets
    -0.65
    orters
    -0.65
    POSITIVE LOGITS
     somew
    1.48
     managed
    1.15
     magically
    1.13
     mirac
    1.09
     manages
    1.07
     somehow
    1.03
     manage
    0.95
     escaped
    0.91
     survived
    0.89
     morphed
    0.89
    Activations Density 0.036%

    No Known Activations