Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17190
    Prev
    Next
    INDEX
    Explanations

    the word "well"

    oai_token-act-pair · gpt-3.5-turbo

    the word "well."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illary
    -0.79
    rely
    -0.73
    hett
    -0.70
    IRO
    -0.69
    liest
    -0.63
    senal
    -0.62
    emonic
    -0.62
    illac
    -0.62
     juggling
    -0.62
     scapego
    -0.61
    POSITIVE LOGITS
    esley
    1.24
    sburg
    0.98
    s
    0.94
    ington
    0.86
    ards
    0.86
    espie
    0.84
    stone
    0.83
    aday
    0.82
    spring
    0.82
    mark
    0.80
    Activations Density 0.028%

    No Known Activations