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. 7-RES-JB
    6. 7654
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "think" is used in a statement

    oai_token-act-pair · gpt-3.5-turbo

    statements of disbelief or skepticism

    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
    è»
    -0.73
    ufact
    -0.69
    redients
    -0.68
    Vers
    -0.67
    udeb
    -0.65
    pez
    -0.65
     pione
    -0.65
    gur
    -0.64
    haar
    -0.64
    autions
    -0.64
    POSITIVE LOGITS
     anybody
    1.10
     anymore
    1.00
     anyone
    1.00
     anything
    0.96
     nor
    0.91
     any
    0.90
     whatsoever
    0.84
     necessarily
    0.82
     EVER
    0.81
     anywhere
    0.80
    Activations Density 0.069%

    No Known Activations