© 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. 8-RES-JB
    11. 1914
    Prev
    Next
    INDEX
    Explanations

    features or capabilities of software applications that allow users to perform various actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms indicating user capabilities or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.74
     Closing
    -0.70
     Worth
    -0.67
    ukemia
    -0.65
     Appears
    -0.65
    fired
    -0.65
     Winning
    -0.65
    Appearances
    -0.64
     Hits
    -0.63
    worn
    -0.62
    POSITIVE LOGITS
     customize
    1.48
     manipulate
    1.32
     specify
    1.21
     simulate
    1.20
     browse
    1.15
     automate
    1.15
     visualize
    1.15
     modify
    1.13
     choose
    1.10
     manually
    1.09
    Activations Density 0.249%

    No Known Activations