© 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. 4-RES-JB
    11. 10086
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "ridiculous"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ridiculous."

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

    No Comments

    Negative Logits
    board
    -0.84
    yer
    -0.81
    wright
    -0.79
    Reviewed
    -0.76
    emis
    -0.73
    maid
    -0.72
    avers
    -0.71
    mediate
    -0.70
    igate
    -0.70
    fman
    -0.70
    POSITIVE LOGITS
     amounts
    1.02
     amount
    0.90
     lengths
    0.89
     proportions
    0.86
     nonsense
    0.85
    NESS
    0.84
    ness
    0.82
     Hercules
    0.81
    nesses
    0.80
     unbeliev
    0.80
    Activations Density 0.030%

    No Known Activations