© 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. 10-RES-JB
    11. 16232
    Prev
    Next
    INDEX
    Explanations

    references to deep exploration, investigations, or uncovering of information

    oai_token-act-pair · gpt-3.5-turbo

    references to "deluge" or overwhelming quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.74
     clipboard
    -0.61
     AFL
    -0.60
     behind
    -0.57
     staging
    -0.57
     goodbye
    -0.56
    ratulations
    -0.56
    SHIP
    -0.56
     dearly
    -0.55
     Stanley
    -0.55
    POSITIVE LOGITS
    uxe
    1.43
    uge
    1.25
    ving
    1.16
    ivery
    1.15
    ights
    1.15
    uded
    1.11
    ayed
    1.07
    icate
    1.04
    phi
    1.03
    usional
    1.03
    Activations Density 0.012%

    No Known Activations