© 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. 12138
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases or examples used to illustrate a point

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "case" with various numerical modifiers indicating different cases or examples

    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
    resent
    -0.68
    onder
    -0.68
     phased
    -0.65
    rush
    -0.64
    orks
    -0.63
     ja
    -0.63
    rones
    -0.62
    arus
    -0.62
    zeb
    -0.62
    swick
    -0.61
    POSITIVE LOGITS
     study
    0.87
     Keen
    0.78
    cmp
    0.77
     scenario
    0.76
     insensitive
    0.75
    fy
    0.74
     histories
    0.72
    cases
    0.71
    esan
    0.71
     Study
    0.71
    Activations Density 0.042%

    No Known Activations