© 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. 107
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people, places, or things

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the token "da" that suggests multiple mentions or a focus on specific subjects

    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
    MENT
    -0.81
     illusions
    -0.71
     Governors
    -0.68
    erous
    -0.67
    ONSORED
    -0.67
    OTOS
    -0.66
    ments
    -0.66
    rored
    -0.66
    sburgh
    -0.65
     Dragonbound
    -0.65
    POSITIVE LOGITS
    isy
    1.12
    emon
    1.12
    uthor
    1.06
    iba
    0.91
    elta
    0.86
    emonic
    0.86
    fters
    0.85
    ichi
    0.85
    ÄŁ
    0.85
    ption
    0.83
    Activations Density 0.012%

    No Known Activations