Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 3781
    Prev
    Next
    INDEX
    Explanations

    verbs related to negative actions, often with a sense of aggression or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "berate" and related forms, indicating a focus on criticism or verbal abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uncture
    -0.90
    ortium
    -0.86
    opsy
    -0.83
    existent
    -0.79
    ramid
    -0.79
    auga
    -0.76
    metics
    -0.74
    idental
    -0.71
    hibit
    -0.71
    efficients
    -0.70
    POSITIVE LOGITS
     ber
    1.45
    keley
    1.11
    anke
    0.80
     Laden
    0.78
    anche
    0.76
    taboola
    0.69
    ger
    0.67
    dan
    0.66
    rill
    0.66
    aser
    0.66
    Activations Density 0.003%

    No Known Activations