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. 4-RES-JB
    6. 18671
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and building relationships

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to community engagement and interaction

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

    No Comments

    Negative Logits
     leaked
    -0.72
     usual
    -0.67
    ãĥĥãĥī
    -0.67
     infamous
    -0.67
     retracted
    -0.64
     deductible
    -0.62
     Fatal
    -0.61
    ãĥĥãĥĪ
    -0.61
    Il
    -0.61
     notorious
    -0.61
    POSITIVE LOGITS
    cellence
    0.97
     perspectives
    0.89
     opportunities
    0.88
     empowerment
    0.88
     transformative
    0.87
     excellence
    0.81
     Dialogue
    0.80
    thood
    0.79
     collaborations
    0.78
     initiatives
    0.78
    Activations Density 0.531%

    No Known Activations