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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 18988
    Prev
    Next
    INDEX
    Explanations

    specific verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Layer 1: Is/Was tokens
    was (will fire on the token was)

    No Comments

    Negative Logits
    inav
    -0.63
     Extend
    -0.54
    edIn
    -0.52
     Suit
    -0.50
     derby
    -0.50
     Which
    -0.49
     generations
    -0.48
     Lowe
    -0.48
    lambda
    -0.47
     Raise
    -0.47
    POSITIVE LOGITS
    nt
    0.97
    hes
    0.85
    wolves
    0.82
    hers
    0.76
    wolf
    0.74
     supposed
    0.72
     definitely
    0.68
    gur
    0.65
    rael
    0.64
     dece
    0.62
    Activations Density 0.237%

    No Known Activations