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. 10-RES-JB
    6. 7603
    Prev
    Next
    INDEX
    Explanations

    mentions of "firsts" or events that are unprecedented

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant milestones or first occurrences involving a president or notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inders
    -0.76
    redients
    -0.76
    Effects
    -0.69
     cries
    -0.69
     shouts
    -0.69
    bags
    -0.67
     Extras
    -0.67
    anges
    -0.67
     hallucinations
    -0.67
    files
    -0.66
    POSITIVE LOGITS
     major
    1.07
     politician
    0.96
     member
    0.91
    major
    0.90
     lawmaker
    0.90
     single
    0.90
     foreign
    0.89
     foreigner
    0.87
     contender
    0.86
     presidential
    0.85
    Activations Density 0.135%

    No Known Activations