© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11383
    Prev
    Next
    INDEX
    Explanations

    mentions of conferences or symposiums, especially named ones

    oai_token-act-pair · gpt-3.5-turbo

    references to symposiums and related events or entities

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

    No Comments

    Negative Logits
    holding
    -0.78
    patrick
    -0.72
     oats
    -0.69
     Palmer
    -0.69
    WARD
    -0.68
    ãģ¦
    -0.68
    LESS
    -0.66
    tan
    -0.64
    ardless
    -0.64
    erness
    -0.62
    POSITIVE LOGITS
    posium
    1.60
    phony
    1.20
    ptoms
    1.15
     Sym
    0.98
    onic
    0.89
    ciplinary
    0.88
    ple
    0.87
    etrical
    0.86
    Sym
    0.85
    pt
    0.85
    Activations Density 0.011%

    No Known Activations