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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8-RES-JB
    6. 18209
    Prev
    Next
    INDEX
    Explanations

    instances of words related to running or moving quickly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "run" and "ran."

    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
     Lauder
    -0.68
    repre
    -0.66
    theless
    -0.63
    alam
    -0.60
     suscept
    -0.59
    olia
    -0.58
    iasco
    -0.58
     defic
    -0.58
    ortium
    -0.57
     subsequ
    -0.57
    POSITIVE LOGITS
    escape
    1.01
    aways
    0.97
    gs
    0.93
     af
    0.89
    away
    0.85
    nin
    0.83
    agate
    0.81
    dy
    0.80
     rampant
    0.80
    around
    0.79
    Activations Density 0.049%

    No Known Activations