© 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. 7-RES-JB
    11. 2025
    Prev
    Next
    INDEX
    Explanations

    technical components or parts mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to various components and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kers
    -0.82
    standing
    -0.79
    fm
    -0.75
    ker
    -0.72
    stretched
    -0.71
    bies
    -0.66
    ipeg
    -0.66
    hur
    -0.66
     Predators
    -0.65
    tale
    -0.65
    POSITIVE LOGITS
     components
    0.93
     parts
    0.88
     component
    0.85
     subsystem
    0.84
     thereof
    0.82
     Components
    0.80
    iation
    0.79
    onents
    0.79
     additive
    0.75
    ivity
    0.73
    Activations Density 0.025%

    No Known Activations