© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2677
    Prev
    Next
    INDEX
    Explanations

    references to parking garages

    oai_token-act-pair · gpt-3.5-turbo

    references to gar (garages or garbage) and barricades in various contexts

    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
     Heller
    -0.67
     Hits
    -0.65
     Collector
    -0.63
    æĸ¹
    -0.63
    lda
    -0.63
    è£ħ
    -0.62
     Illustrated
    -0.61
     Ceres
    -0.61
    CEPT
    -0.60
     GOODMAN
    -0.60
    POSITIVE LOGITS
    tered
    0.95
    unte
    0.90
    tering
    0.90
    bled
    0.88
    aded
    0.88
    ood
    0.86
    bles
    0.85
    ilities
    0.79
    estation
    0.79
    ading
    0.78
    Activations Density 0.089%

    No Known Activations