© 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. 7463
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and operations that are "up and running."

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" and its various usages in sentences

    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
    regate
    -0.79
    prise
    -0.78
    ãĤ´ãĥ³
    -0.76
    rued
    -0.76
    ruce
    -0.74
    ute
    -0.73
    ibble
    -0.73
    ylon
    -0.72
    enture
    -0.72
    UAL
    -0.71
    POSITIVE LOGITS
     ready
    1.49
     awaiting
    1.34
     waiting
    1.16
     poised
    1.13
     behaving
    1.12
     alive
    1.05
     unavailable
    1.04
     primed
    1.03
     functioning
    1.02
     incapable
    1.01
    Activations Density 0.219%

    No Known Activations