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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7807
    Prev
    Next
    INDEX
    Explanations

    the verb "be" with different versions and combinations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the verb "be" in various forms

    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
    âĨij
    -0.66
     Kurd
    -0.63
     Palestin
    -0.59
     Examiner
    -0.58
     hoops
    -0.57
     Crunch
    -0.56
     tandem
    -0.54
     appointments
    -0.54
     Selection
    -0.54
     Oval
    -0.53
    POSITIVE LOGITS
    gins
    1.11
    hemoth
    1.08
    heading
    1.08
    ijing
    1.06
    acons
    1.06
    arers
    0.99
    league
    0.98
    yond
    0.97
    ardless
    0.95
    friends
    0.94
    Activations Density 0.036%

    No Known Activations