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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 944
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the end of content markers or delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Azerb
    -0.74
     prest
    -0.69
    edIn
    -0.68
     Kurd
    -0.67
    âĨij
    -0.67
    osate
    -0.67
     srfAttach
    -0.65
     Examiner
    -0.60
     Seym
    -0.60
    0001
    -0.60
    POSITIVE LOGITS
    Í
    0.86
    ams
    0.75
    heading
    0.72
    yond
    0.70
    ardless
    0.70
    yon
    0.70
    ige
    0.70
    eps
    0.69
    erc
    0.67
    hemoth
    0.67
    Activations Density 0.031%

    No Known Activations