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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 9395
    Prev
    Next
    INDEX
    Explanations

    words related to spinning or derivative works

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spin" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.68
    ermott
    -0.66
     Mellon
    -0.63
     Frie
    -0.62
    avis
    -0.61
     Newsp
    -0.60
    essors
    -0.58
     Commodore
    -0.57
     Scores
    -0.57
     Puzz
    -0.57
    POSITIVE LOGITS
    ners
    1.47
    eless
    1.05
    ned
    1.05
    othal
    1.01
    offs
    0.96
    wheel
    0.89
    off
    0.87
    balls
    0.84
    otom
    0.82
    kered
    0.82
    Activations Density 0.057%

    No Known Activations