© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and business operations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to internet service providers and their regulatory activities

    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
    /-
    -0.70
    ministic
    -0.68
    perture
    -0.65
    VALUE
    -0.65
    ileged
    -0.63
    \\
    -0.61
     dull
    -0.60
    construct
    -0.60
     unus
    -0.59
    estamp
    -0.57
    POSITIVE LOGITS
     recently
    1.04
     controvers
    0.81
     recent
    0.81
     lately
    0.79
     renewed
    0.73
    recent
    0.73
     publicized
    0.73
     Recently
    0.73
     lawmakers
    0.72
    announced
    0.72
    Activations Density 1.060%

    No Known Activations