© 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. 10131
    Prev
    Next
    INDEX
    Explanations

    words related to giving directions or commands

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "instruct" and its derivatives

    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
     Roses
    -0.71
     á
    -0.70
    buck
    -0.69
     Balkans
    -0.65
     âĻ
    -0.64
    adjusted
    -0.64
    addons
    -0.64
    Ott
    -0.64
     Bok
    -0.63
    á
    -0.62
    POSITIVE LOGITS
     instruct
    0.97
     instructed
    0.90
    eering
    0.88
    htaking
    0.86
     instruction
    0.86
     manuals
    0.85
     instructors
    0.83
     Instruct
    0.82
     certific
    0.81
    tale
    0.81
    Activations Density 0.016%

    No Known Activations