© 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. 11188
    Prev
    Next
    INDEX
    Explanations

    range intervals such as "5-8" expressed in a numeric format

    oai_token-act-pair · gpt-3.5-turbo

    specific sports-related statistics and performance metrics

    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
     brakes
    -0.75
     Mermaid
    -0.70
     Yorkers
    -0.66
     Poles
    -0.63
     icons
    -0.63
     Ukrainians
    -0.61
     buffs
    -0.60
     laure
    -0.60
     recru
    -0.60
     fares
    -0.59
    POSITIVE LOGITS
    occupied
    0.92
     nutshell
    0.90
     contexts
    0.88
     vicinity
    0.86
     context
    0.84
    perate
    0.83
     guise
    0.78
    stakes
    0.78
    imester
    0.76
    iverse
    0.76
    Activations Density 0.559%

    No Known Activations