© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 23212
    Prev
    Next
    INDEX
    Explanations

    be verbs and related forms (e.g., "is," "are," "were")

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Difference
    -0.63
    uctor
    -0.58
     Titanic
    -0.57
     Radius
    -0.57
     Sunshine
    -0.56
    eteen
    -0.56
     Detail
    -0.55
     Capture
    -0.55
     Quantity
    -0.53
     Memories
    -0.53
    POSITIVE LOGITS
     therefore
    1.74
     consequently
    1.70
     thus
    1.35
     accordingly
    1.34
     thereby
    1.25
     hence
    1.18
     furthermore
    1.13
     consequ
    1.09
     thereafter
    1.08
     moreover
    1.07
    Activations Density 0.309%

    No Known Activations