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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 13204
    Prev
    Next
    INDEX
    Explanations

    phrases related to raising or increasing something, such as alerts, issues, money, hands, or terror levels

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "raise" and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.74
     Antar
    -0.72
    ucci
    -0.67
    umerable
    -0.65
    ica
    -0.62
    mys
    -0.62
    Cola
    -0.62
    neys
    -0.61
    swick
    -0.60
    destruct
    -0.60
    POSITIVE LOGITS
     eyebrows
    1.12
     eyebrow
    0.95
     ire
    0.85
     suspicions
    0.84
     objections
    0.79
     awareness
    0.78
     stairs
    0.78
     suspicion
    0.77
     Awareness
    0.75
    aura
    0.69
    Activations Density 0.108%

    No Known Activations