© 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. 0-RES-JB
    11. 6347
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or topic related to "Raw."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Raw" in the context of WWE events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.76
     plaque
    -0.74
    pillar
    -0.68
     labyrinth
    -0.68
    éŃĶ
    -0.66
     forgiven
    -0.63
    ophon
    -0.63
     amusement
    -0.63
    illion
    -0.62
     inhibitors
    -0.62
    POSITIVE LOGITS
     Raw
    4.08
    Raw
    2.75
     RAW
    2.22
     raw
    1.53
    raw
    1.36
    RAW
    1.19
     Pure
    1.13
     Pow
    1.00
     Wrestle
    1.00
     Straw
    0.96
    Activations Density 0.016%

    No Known Activations