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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 20028
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "ough"

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the substring "ough"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     porn
    -0.75
     meter
    -0.66
     se
    -0.64
     zo
    -0.64
     oper
    -0.61
     Reloaded
    -0.60
     liberated
    -0.60
     lim
    -0.59
     repe
    -0.59
     plac
    -0.59
    POSITIVE LOGITS
    ough
    4.37
    oug
    2.04
    OUGH
    1.93
    augh
    1.39
    ogh
    1.35
    ugh
    1.31
    rough
    1.25
    agh
    1.24
    umbers
    1.08
    aug
    1.06
    Activations Density 0.007%

    No Known Activations