© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    terms related to autonomous technology

    oai_token-act-pair · gpt-3.5-turbo

    references to autonomous technologies and systems

    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
    imaru
    -0.83
    swick
    -0.83
    ttp
    -0.81
    ulhu
    -0.79
    eus
    -0.75
    tk
    -0.74
    colo
    -0.73
    Ey
    -0.73
    dn
    -0.70
    Express
    -0.70
    POSITIVE LOGITS
    onomous
    1.27
     autonomous
    0.97
     autonom
    0.92
     braking
    0.87
    ¥ŀ
    0.81
    onomy
    0.79
     republic
    0.76
     robotic
    0.76
     satell
    0.74
     minded
    0.73
    Activations Density 0.007%

    No Known Activations