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. 11948
    Prev
    Next
    INDEX
    Explanations

    actions related to reversing or undoing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "reverse" in various contexts related to processes or actions

    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
    Interstitial
    -1.04
    lished
    -1.00
    chens
    -0.84
    akov
    -0.82
    lov
    -0.82
    chen
    -0.82
    rum
    -0.81
    rics
    -0.80
    pur
    -0.79
    rine
    -0.77
    POSITIVE LOGITS
     chronological
    1.08
     engineer
    0.92
     engineered
    0.78
     engineering
    0.77
     psychology
    0.76
     causation
    0.75
     caus
    0.74
    engineering
    0.72
     symmetry
    0.70
     direction
    0.68
    Activations Density 0.035%

    No Known Activations