© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4759
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and "were"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Response
    -0.64
    negie
    -0.64
     Fail
    -0.63
     Liberties
    -0.63
    osate
    -0.62
     Cosponsors
    -0.61
    rss
    -0.61
     Dimensions
    -0.60
     Rug
    -0.60
    encies
    -0.59
    POSITIVE LOGITS
     wrapping
    1.24
     preparing
    1.24
     finishing
    1.24
     drying
    1.13
     recovering
    1.12
     assembling
    1.12
     leaving
    1.09
     completing
    1.08
     packing
    1.07
     winding
    1.06
    Activations Density 0.109%

    No Known Activations