© 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. 12726
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions, business, and medical actions

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or characters that indicate special formatting or typographical elements

    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
     Osw
    -0.72
     Eck
    -0.70
     ILCS
    -0.63
     Damon
    -0.62
     Willow
    -0.62
     untold
    -0.62
    BuyableInstoreAndOnline
    -0.62
     Heck
    -0.62
     GOODMAN
    -0.59
     Asuka
    -0.59
    POSITIVE LOGITS
    tion
    1.31
    tions
    1.28
     tion
    1.11
    cation
    1.10
    ctive
    1.07
    mental
    1.06
    cence
    1.03
    ciation
    1.01
    tal
    0.99
    lation
    0.98
    Activations Density 0.070%

    No Known Activations