© 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. 15685
    Prev
    Next
    INDEX
    Explanations

    proper nouns denoting specific institutions or entities

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and articles in sentences

    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
    aments
    -0.71
     diplom
    -0.63
     afar
    -0.61
    åij
    -0.60
    icut
    -0.60
    naires
    -0.60
     respectively
    -0.58
    çİĭ
    -0.58
    tenance
    -0.58
     flick
    -0.58
    POSITIVE LOGITS
    itialized
    0.85
    semb
    0.74
    slaught
    0.72
    herent
    0.71
     Month
    0.69
    omaly
    0.68
    Cap
    0.67
    lex
    0.65
    tes
    0.65
    hib
    0.64
    Activations Density 0.144%

    No Known Activations