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. 8-RES-JB
    6. 23023
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to raising questions or concerns

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate raising questions or doubts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vanquished
    -0.70
     survives
    -0.65
    \-
    -0.62
    melon
    -0.62
    ta
    -0.62
     Healer
    -0.61
    ians
    -0.60
    ian
    -0.60
     conquered
    -0.60
     Thou
    -0.60
    POSITIVE LOGITS
     suspicions
    1.34
     eyebrows
    1.29
     doubts
    1.22
     suspicion
    1.15
     questions
    1.14
     alarms
    1.12
     alarm
    1.10
     concerns
    1.07
     fears
    1.00
     tensions
    0.94
    Activations Density 0.068%

    No Known Activations