© 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. 4-RES-JB
    11. 824
    Prev
    Next
    INDEX
    Explanations

    words related to entities, such as companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of specificity or particularity

    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
    inav
    -0.97
    auder
    -0.78
    odium
    -0.76
    kef
    -0.74
    ask
    -0.72
    yrinth
    -0.71
    ergy
    -0.67
    iston
    -0.66
    akespe
    -0.66
    etsk
    -0.64
    POSITIVE LOGITS
     Peb
    0.87
     Pwr
    0.78
    -------
    0.74
    Hash
    0.73
    ful
    0.69
    yy
    0.69
     charms
    0.68
    phal
    0.67
     Principle
    0.67
    leness
    0.66
    Activations Density 0.030%

    No Known Activations