© 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. 10-RES-JB
    11. 4656
    Prev
    Next
    INDEX
    Explanations

    locations or settings in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the preposition "in" in various contexts

    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
    $$$$
    -0.80
    ella
    -0.76
    0000000000000000
    -0.74
    "},{"
    -0.74
    ãĤ¼ãĤ¦ãĤ¹
    -0.73
    onica
    -0.72
    000000
    -0.71
    inx
    -0.69
    HAEL
    -0.68
    MpServer
    -0.65
    POSITIVE LOGITS
     recent
    1.73
     past
    1.28
     lately
    1.17
     previous
    1.13
    recent
    1.10
     successive
    1.02
     years
    1.01
     decades
    1.00
     vain
    0.97
     Recent
    0.97
    Activations Density 0.185%

    No Known Activations