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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9432
    Prev
    Next
    INDEX
    Explanations

    verbs in past or present participles

    oai_token-act-pair · gpt-3.5-turbo

    past and present tense forms of the verb "to be."

    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
     Highlands
    -0.64
     Valley
    -0.60
     lur
    -0.60
     Rosenberg
    -0.59
    acters
    -0.59
    rocket
    -0.58
    izable
    -0.58
     Lag
    -0.57
    =-=-
    -0.56
    ertodd
    -0.56
    POSITIVE LOGITS
     supposed
    1.15
     accustomed
    1.03
     doing
    0.98
     aiming
    0.97
     able
    0.96
     experiencing
    0.96
     talking
    0.94
     wont
    0.90
     referring
    0.88
     hoping
    0.88
    Activations Density 0.128%

    No Known Activations