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. 0-RES-JB
    6. 17780
    Prev
    Next
    INDEX
    Explanations

    mentions of former individuals in various professional or political roles

    oai_token-act-pair · gpt-3.5-turbo

    references to former individuals or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     push
    -0.68
     prints
    -0.68
     sequences
    -0.67
     rush
    -0.64
     console
    -0.63
     work
    -0.63
     digit
    -0.63
     catalog
    -0.62
    ry
    -0.61
     sequencing
    -0.61
    POSITIVE LOGITS
    Former
    3.48
     Former
    2.52
    former
    1.83
     former
    1.72
    formerly
    1.45
    Senior
    1.30
    Veter
    1.22
    Actor
    1.19
    Executive
    1.17
    Attorney
    1.15
    Activations Density 0.016%

    No Known Activations