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. 10-RES-JB
    6. 3879
    Prev
    Next
    INDEX
    Explanations

    names of people or entities in a news context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or institutions involved in significant activities or decisions

    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
     Definitions
    -0.70
     clich
    -0.70
     contrasts
    -0.69
    inguished
    -0.67
     commons
    -0.67
    simple
    -0.66
     contrast
    -0.66
    azeera
    -0.66
    basic
    -0.64
    inctions
    -0.63
    POSITIVE LOGITS
     secretly
    1.15
     plans
    0.98
     rumored
    0.96
     leaked
    0.92
     blackmail
    0.91
     planned
    0.89
     mull
    0.87
     undisclosed
    0.84
     imminent
    0.84
     plotting
    0.84
    Activations Density 0.454%

    No Known Activations