© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 17882
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ado" at various intensities, potentially focusing on a specific context or person named "Maldonado."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ado"

    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
    utive
    -0.79
     detrim
    -0.69
    ippi
    -0.68
     reluct
    -0.67
    Ö¼
    -0.67
    utable
    -0.66
     divide
    -0.65
    ASE
    -0.63
    ITED
    -0.63
     clipboard
    -0.61
    POSITIVE LOGITS
    quez
    0.99
    ado
    0.91
    osta
    0.89
    quit
    0.88
    eno
    0.82
    illo
    0.80
    ques
    0.74
     Squadron
    0.74
    jo
    0.74
     Libre
    0.72
    Activations Density 0.009%

    No Known Activations