© 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. 9813
    Prev
    Next
    INDEX
    Explanations

    references to individual components or component parts in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to parts or elements of a system or object

    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
    standing
    -0.81
    kers
    -0.78
    bies
    -0.73
    ipeg
    -0.72
    stretched
    -0.70
    ker
    -0.69
     Predators
    -0.69
    sle
    -0.68
     Croat
    -0.66
     Topic
    -0.65
    POSITIVE LOGITS
     components
    0.88
     thereof
    0.87
     parts
    0.85
     component
    0.82
     Components
    0.79
     subsystem
    0.78
    iation
    0.75
    onents
    0.73
     Component
    0.73
     extracted
    0.72
    Activations Density 0.026%

    No Known Activations