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. 3-RES-JB
    6. 10929
    Prev
    Next
    INDEX
    Explanations

    adjectives related to permanence or irreversibility

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "irreversible."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.80
    ramid
    -0.79
     Hunters
    -0.77
     Trials
    -0.73
    auri
    -0.70
    ucket
    -0.70
     Butterfly
    -0.70
    amide
    -0.69
    oaded
    -0.68
    wagen
    -0.66
    POSITIVE LOGITS
    voc
    1.18
     irre
    1.12
    parable
    0.91
    lev
    0.85
    ality
    0.80
    agan
    0.79
    olit
    0.79
    itable
    0.79
    em
    0.77
    heat
    0.76
    Activations Density 0.011%

    No Known Activations