© 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. 23344
    Prev
    Next
    INDEX
    Explanations

    mentions of specific Tesla car models

    oai_token-act-pair · gpt-3.5-turbo

    references to specific Tesla vehicle models

    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
    olulu
    -0.85
    ulhu
    -0.78
    èª
    -0.78
    Downloadha
    -0.77
     darkest
    -0.70
    angers
    -0.68
     Clare
    -0.66
    çĦ
    -0.65
    raf
    -0.65
    azar
    -0.64
    POSITIVE LOGITS
     Model
    1.17
     Models
    1.01
    Model
    0.92
     Mayhem
    0.83
    model
    0.77
     Penal
    0.76
    urer
    0.75
    eer
    0.73
    Http
    0.72
     models
    0.70
    Activations Density 0.006%

    No Known Activations