© 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 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. 6139
    Prev
    Next
    INDEX
    Explanations

    numbers representing statistical data and figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of end-of-text markers

    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
     newsp
    -0.86
    undai
    -0.82
    lied
    -0.81
     proble
    -0.79
     administr
    -0.77
     challeng
    -0.76
    nesday
    -0.76
    itiz
    -0.73
     discipl
    -0.71
     pse
    -0.71
    POSITIVE LOGITS
     ILCS
    1.42
     SHARES
    1.24
    çĶ°
    1.07
     Shares
    1.02
     Explicit
    0.98
     Pages
    0.96
    804
    0.95
    807
    0.95
    765
    0.95
    KB
    0.94
    Activations Density 0.088%

    No Known Activations