© 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. 8-RES-JB
    11. 16677
    Prev
    Next
    INDEX
    Explanations

    names and terms with the suffix "-um" or "-um" itself

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the syllable "um" and related variations in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĩ
    -0.68
    hips
    -0.68
     Drift
    -0.68
    alty
    -0.67
    eller
    -0.65
    ttes
    -0.65
     Cosponsors
    -0.64
     lure
    -0.63
     chars
    -0.62
     Morales
    -0.61
    POSITIVE LOGITS
    pty
    1.34
    ming
    1.28
    mers
    1.26
    plin
    1.14
    plings
    1.08
    pling
    1.07
    ceed
    1.01
    mer
    1.00
    ptive
    0.99
    ulative
    0.97
    Activations Density 0.057%

    No Known Activations