© 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. 9-RES-JB
    11. 14150
    Prev
    Next
    INDEX
    Explanations

    special characters, numbers, and dates within a text

    oai_token-act-pair · gpt-3.5-turbo

    numeric data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     materially
    -0.68
     antit
    -0.64
     turnover
    -0.62
    ivably
    -0.61
     restitution
    -0.60
     substant
    -0.60
     diseng
    -0.59
     allied
    -0.59
     rooting
    -0.59
     meantime
    -0.58
    POSITIVE LOGITS
    Welcome
    1.22
    ³³³³³³³³³³³³³³³³
    1.21
    Introduction
    1.17
    hello
    1.16
    Posted
    1.16
    Overview
    1.13
    Hello
    1.11
    ³³³³³³³³
    1.07
    ³³³
    1.07
    Definition
    1.05
    Activations Density 0.177%

    No Known Activations