© 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. 4960
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a short noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in a" or variations indicating context or location

    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
     unemploy
    -0.70
     someday
    -0.70
     TRUE
    -0.65
     (&
    -0.65
     nurt
    -0.64
    digy
    -0.62
    ((
    -0.61
    $$
    -0.59
     Unsure
    -0.59
     innoc
    -0.59
    POSITIVE LOGITS
     remarks
    1.03
     accordance
    1.01
     defiance
    0.98
     Brussels
    0.97
    aug
    0.94
     response
    0.92
     parliament
    0.92
    spect
    0.89
     unison
    0.89
    jured
    0.86
    Activations Density 0.200%

    No Known Activations