© 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 EvalsExportsinterp-engineNEWAPI 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. 24257
    Prev
    Next
    INDEX
    Explanations

    phrases related to warning or advising against certain actions

    oai_token-act-pair · gpt-3.5-turbo

    economic and commercial terms related to products and business practices

    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
    aughs
    -0.76
    issan
    -0.59
    assis
    -0.58
    jah
    -0.57
    olars
    -0.57
    phia
    -0.56
     Battery
    -0.55
    UCK
    -0.54
    ieri
    -0.54
     airst
    -0.53
    POSITIVE LOGITS
     differently
    0.95
     solely
    0.90
     resembling
    0.84
     containing
    0.84
     purely
    0.82
     outside
    0.80
     exclusively
    0.80
     directly
    0.78
     WITHOUT
    0.77
    outside
    0.77
    Activations Density 0.510%

    No Known Activations