© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9453
    Prev
    Next
    INDEX
    Explanations

    numbers, items on a list, and related information in structured formats like time or location

    oai_token-act-pair · gpt-3.5-turbo

    time and date-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shedding
    -0.53
     surrog
    -0.53
     assum
    -0.53
     overl
    -0.53
     infl
    -0.52
     redund
    -0.52
     toget
    -0.52
     narrowing
    -0.51
     undermin
    -0.51
     destro
    -0.51
    POSITIVE LOGITS
     âĵĺ
    0.90
     Location
    0.70
     Joined
    0.67
    ;;;;;;;;;;;;
    0.66
     Profile
    0.64
     à¨
    0.64
     Apr
    0.63
     08
    0.62
     ãĥ
    0.62
     07
    0.61
    Activations Density 0.627%

    No Known Activations