© 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. 4-RES-JB
    11. 10158
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Audi" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of automotive brands, specifically Audi and Airbus

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

    No Comments

    Negative Logits
    arters
    -0.85
    ledge
    -0.84
    FUL
    -0.76
    xual
    -0.76
    fulness
    -0.74
    pter
    -0.74
    tails
    -0.73
    ledged
    -0.73
    vous
    -0.73
    laus
    -0.72
    POSITIVE LOGITS
    obook
    1.25
    ophile
    0.89
     Audi
    0.84
    obile
    0.81
    okin
    0.78
    orem
    0.77
    oph
    0.76
    Consumer
    0.73
    omach
    0.72
    ometer
    0.70
    Activations Density 0.006%

    No Known Activations