© 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. 1-RES-JB
    11. 8572
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Ferrari"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Ferrari brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.85
    orative
    -0.81
    umbn
    -0.79
    endants
    -0.76
    itcher
    -0.75
    alid
    -0.70
    olver
    -0.69
    retched
    -0.69
    psc
    -0.67
    mble
    -0.67
    POSITIVE LOGITS
     Ferrari
    1.17
    ettel
    0.89
     dealership
    0.81
     resil
    0.79
     Fior
    0.78
     parked
    0.78
    ucci
    0.77
    illo
    0.75
    ilion
    0.73
     racing
    0.71
    Activations Density 0.009%

    No Known Activations