© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 13382
    Prev
    Next
    INDEX
    Explanations

    the word "bona" and words related to or containing the word "bona"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bon" or its variations, indicating a focus on something related to good quality or authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nicotine
    -0.72
    PRES
    -0.67
    VERTIS
    -0.67
     Symptoms
    -0.64
     Marijuana
    -0.64
    Snake
    -0.64
     Patient
    -0.63
    STD
    -0.63
     Editorial
    -0.62
    ODE
    -0.62
    POSITIVE LOGITS
     bon
    1.17
    bon
    1.05
     fide
    1.02
    uses
    0.97
    Bon
    0.93
    neau
    0.90
    bat
    0.88
    uit
    0.86
    eless
    0.85
    bons
    0.84
    Activations Density 0.003%

    No Known Activations