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. 10-RES-JB
    6. 20766
    Prev
    Next
    INDEX
    Explanations

    verbs related to criticizing and attacking

    oai_token-act-pair · gpt-3.5-turbo

    strong negative actions or criticisms directed at individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hazard
    -0.73
    emetery
    -0.73
    kj
    -0.73
    Untitled
    -0.71
    redits
    -0.71
    knit
    -0.70
    pole
    -0.69
    mad
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.69
    istics
    -0.67
    POSITIVE LOGITS
     critics
    1.10
     liberals
    0.92
     environmentalists
    0.89
     hypocrisy
    0.89
     reporters
    0.89
     criticisms
    0.88
     President
    0.88
     unnamed
    0.87
     commenters
    0.86
     suggestions
    0.86
    Activations Density 0.149%

    No Known Activations