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. 1-RES-JB
    6. 12507
    Prev
    Next
    INDEX
    Explanations

    technical terms or buzzwords related to progress, development, or growth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to progress and negative impacts over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     landsl
    -0.72
    eq
    -0.69
    checking
    -0.66
    election
    -0.65
     rodents
    -0.64
     parties
    -0.64
     drift
    -0.63
     chimpanzees
    -0.62
     pse
    -0.62
    gencies
    -0.61
    POSITIVE LOGITS
    ACTED
    0.85
    ASED
    0.83
    SHIP
    0.71
    SourceFile
    0.70
     Rapids
    0.69
     impacted
    0.68
    OTUS
    0.65
     Hendricks
    0.65
    ï¸
    0.63
     molded
    0.62
    Activations Density 0.061%

    No Known Activations