© 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. 18569
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software, applications, and technologies

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" used in various contexts

    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
    ONE
    -0.65
     Doctrine
    -0.61
    ODY
    -0.59
     Counsel
    -0.58
     Domestic
    -0.57
    Desk
    -0.57
    hat
    -0.56
    hips
    -0.56
    EngineDebug
    -0.56
     Conference
    -0.55
    POSITIVE LOGITS
     incorporates
    1.17
     utilizes
    1.17
     combines
    1.15
     resembles
    1.09
     accompanies
    1.08
     integrates
    1.06
     encompasses
    1.04
     enhances
    1.03
     collects
    1.02
     extends
    1.02
    Activations Density 0.215%

    No Known Activations