© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 24386
    Prev
    Next
    INDEX
    Explanations

    strings related to technical document formatting such as page numbers and section headers

    oai_token-act-pair · gpt-3.5-turbo

    structured data related to ratings and reviews

    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
     arming
    -0.70
     militar
    -0.67
     ÂŃ
    -0.67
    fman
    -0.67
     contingency
    -0.66
     stip
    -0.63
     deline
    -0.61
     dispers
    -0.60
     bodily
    -0.59
     arrest
    -0.59
    POSITIVE LOGITS
    Reviewer
    1.27
     Views
    1.19
     Tags
    1.19
    Joined
    1.14
    Posted
    1.13
     Comments
    1.12
     Rating
    1.12
     Reviews
    1.06
     Reply
    1.04
     Downloads
    1.03
    Activations Density 0.230%

    No Known Activations