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. 7-RES-JB
    6. 23400
    Prev
    Next
    INDEX
    Explanations

    instances where someone expresses a strong opinion or viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "express" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.70
     Coffin
    -0.66
     topple
    -0.66
    jack
    -0.65
    etheless
    -0.64
    ney
    -0.64
    neys
    -0.63
     Journalists
    -0.63
     Straight
    -0.63
    osate
    -0.62
    POSITIVE LOGITS
     displeasure
    1.13
     doubts
    1.02
     concerns
    0.95
     condolences
    0.93
     remorse
    0.93
     gratitude
    0.92
     reservations
    0.89
     frustrations
    0.88
     dissatisfaction
    0.88
     sympathy
    0.88
    Activations Density 0.042%

    No Known Activations