© 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 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. 0-RES-JB
    11. 13086
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "Around" followed by a number indicating a quantity or a location

    oai_token-act-pair · gpt-3.5-turbo

    the word "Around" and its various usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deduction
    -0.68
     incapable
    -0.64
     relinqu
    -0.61
    lt
    -0.61
     command
    -0.61
     otherwise
    -0.61
     ren
    -0.60
     borrower
    -0.60
     equ
    -0.58
     biological
    -0.58
    POSITIVE LOGITS
     Around
    3.49
    Around
    3.37
    around
    2.18
     around
    1.71
     Between
    1.28
    Across
    1.23
    About
    1.23
    Between
    1.23
     Across
    1.23
     Towards
    1.22
    Activations Density 0.010%

    No Known Activations