© 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. 9-RES-JB
    11. 4168
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and dates

    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
     Causes
    -0.61
     ACTIONS
    -0.60
     Explan
    -0.59
     gib
    -0.58
     Poles
    -0.58
    hed
    -0.57
     VIDEOS
    -0.57
    imate
    -0.55
     Fib
    -0.55
    hes
    -0.55
    POSITIVE LOGITS
    -'
    0.88
     alongside
    0.85
     graduating
    0.77
    successfully
    0.73
     starring
    0.69
     earning
    0.69
     alone
    0.69
     unsuccessfully
    0.68
    alli
    0.66
     specializing
    0.65
    Activations Density 0.195%

    No Known Activations