© 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. 9914
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions and processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to permissions and regulations

    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
     failures
    -0.62
     fail
    -0.57
     Struggle
    -0.57
     failure
    -0.57
     trouble
    -0.56
    govtrack
    -0.54
     frustration
    -0.54
     failing
    -0.53
     fails
    -0.52
    fail
    -0.52
    POSITIVE LOGITS
     arrang
    0.61
    Ħ¢
    0.56
     livest
    0.54
    soever
    0.53
    nce
    0.52
     describ
    0.52
    SIZE
    0.51
    Pear
    0.51
    acent
    0.50
    beit
    0.48
    Activations Density 1.199%

    No Known Activations