© 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. 3-RES-JB
    11. 15398
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nut" or variations of the word "nut"

    oai_token-act-pair · gpt-3.5-turbo

    references to nuts, particularly walnuts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥİ
    -0.80
     transient
    -0.69
    ngth
    -0.65
     Plasma
    -0.64
     bargaining
    -0.64
     diluted
    -0.61
     Esper
    -0.59
     rece
    -0.59
     comparative
    -0.59
     slight
    -0.58
    POSITIVE LOGITS
    rient
    1.31
    ritional
    1.24
    rients
    1.24
    rition
    1.15
    nut
    1.09
    meg
    0.97
    ricia
    0.94
    nuts
    0.92
    elia
    0.90
    tall
    0.89
    Activations Density 0.009%

    No Known Activations