© 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. 11155
    Prev
    Next
    INDEX
    Explanations

    names or words with 'ee' in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence 'ee' in various contexts

    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
    ãĥķãĤ©
    -0.83
    ãĤ¤ãĥĪ
    -0.75
     traff
    -0.74
     tremend
    -0.72
     obesity
    -0.70
    iques
    -0.69
     anomal
    -0.66
     impossibility
    -0.66
    ãĤ¤
    -0.62
    ifiable
    -0.60
    POSITIVE LOGITS
    pee
    1.06
    gee
    1.02
    bies
    0.99
    ee
    0.97
    bling
    0.95
    ffe
    0.94
    zer
    0.94
    zie
    0.91
    EEE
    0.90
    zza
    0.90
    Activations Density 0.010%

    No Known Activations