© 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. 8-RES-JB
    11. 18517
    Prev
    Next
    INDEX
    Explanations

    Proper names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to influential people and notable entities, often in the context of their achievements or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cybersecurity
    -0.57
     inherit
    -0.55
     privacy
    -0.55
     fundamentally
    -0.54
    âĶĢâĶĢ
    -0.53
     watchdog
    -0.52
     screenshot
    -0.52
     GamerGate
    -0.51
     counterterrorism
    -0.51
     lightly
    -0.51
    POSITIVE LOGITS
    ona
    0.74
    oya
    0.71
    ilda
    0.69
    ussia
    0.68
    ija
    0.67
    tec
    0.67
    avia
    0.66
    oco
    0.66
    ora
    0.66
    aida
    0.66
    Activations Density 0.639%

    No Known Activations