© 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. 8-RES-JB
    11. 7810
    Prev
    Next
    INDEX
    Explanations

    words related to pricing or setting values

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with technical specifications or attributes related to products and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sack
    -0.71
    eeks
    -0.71
    hur
    -0.69
    女
    -0.67
    rance
    -0.67
    Found
    -0.67
    acio
    -0.65
    umbn
    -0.63
    roma
    -0.63
    vous
    -0.63
    POSITIVE LOGITS
     differently
    1.08
     accordingly
    1.01
     correctly
    0.90
     by
    0.89
     incorrectly
    0.88
    ependent
    0.87
     appropriately
    0.85
     externally
    0.83
     properly
    0.82
    ulously
    0.80
    Activations Density 0.210%

    No Known Activations