© 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. 2-RES-JB
    11. 3950
    Prev
    Next
    INDEX
    Explanations

    references to specific car brands

    oai_token-act-pair · gpt-3.5-turbo

    mentions of automobile brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.97
    bern
    -0.86
    itives
    -0.86
    hips
    -0.80
    icion
    -0.78
    Reviewer
    -0.78
    olulu
    -0.77
    hip
    -0.76
    Ĥ¬
    -0.73
    ulton
    -0.73
    POSITIVE LOGITS
     Chrysler
    1.11
     Motors
    0.85
     dealership
    0.84
     Township
    0.81
     Enterprises
    0.80
     Jeep
    0.75
     automakers
    0.75
     Corporation
    0.74
    unia
    0.73
    ota
    0.73
    Activations Density 0.010%

    No Known Activations