© 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. 9-RES-JB
    11. 17257
    Prev
    Next
    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating pros and cons or criticisms regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.77
    tenance
    -0.75
    washer
    -0.73
    tle
    -0.73
    chet
    -0.72
    externalActionCode
    -0.69
    bow
    -0.69
    arta
    -0.68
    lems
    -0.68
    umin
    -0.68
    POSITIVE LOGITS
     having
    1.16
     relying
    1.11
     adopting
    1.10
     trusting
    1.08
     letting
    1.05
     pretending
    1.04
     owning
    1.02
     keeping
    1.00
     believing
    0.98
     abandoning
    0.97
    Activations Density 0.226%

    No Known Activations