© 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. 961
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "car" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to cars or automobile-related concepts

    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
     Flavoring
    -0.86
     Seym
    -0.85
    xual
    -0.76
    scl
    -0.74
    edIn
    -0.74
    naires
    -0.69
    enance
    -0.68
    iversal
    -0.68
    é¾įå¥ij士
    -0.68
     Dull
    -0.68
    POSITIVE LOGITS
    ousel
    1.53
    riages
    1.44
    penter
    1.42
    rera
    1.14
    riage
    1.12
     dealership
    1.06
    negie
    1.04
    olina
    1.00
    seat
    0.94
    wash
    0.92
    Activations Density 0.049%

    No Known Activations