© 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. 2-RES-JB
    11. 9346
    Prev
    Next
    INDEX
    Explanations

    words related to organized group movements or events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates associated with events or marches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soluble
    -0.71
     permissible
    -0.67
     Vul
    -0.65
    ricular
    -0.65
     vacancy
    -0.64
    fixed
    -0.64
    vae
    -0.63
     retained
    -0.63
    levant
    -0.62
    egg
    -0.62
    POSITIVE LOGITS
     march
    1.04
    igraph
    0.98
     marches
    0.97
     marched
    0.95
    iage
    0.95
     marching
    0.92
    ĸļ
    0.82
    athon
    0.79
    naire
    0.77
    oppable
    0.74
    Activations Density 0.012%

    No Known Activations