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

    Neuronpedia

    APICircuit 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. 13190
    Prev
    Next
    INDEX
    Explanations

    references to individuals taking positions of power or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political figures or events marked by a change in leadership

    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
    aminer
    -0.84
    alog
    -0.80
     Cosponsors
    -0.74
     Naked
    -0.69
    AE
    -0.68
    Sing
    -0.68
     Analog
    -0.68
    Snake
    -0.68
     nig
    -0.66
    ocamp
    -0.66
    POSITIVE LOGITS
     predecessor
    1.00
     decree
    0.98
     predecessors
    0.97
     era
    0.93
     reforms
    0.92
     sacked
    0.92
     overhaul
    0.90
     Era
    0.87
     dictatorship
    0.87
     successors
    0.87
    Activations Density 1.096%

    No Known Activations