© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 19460
    Prev
    Next
    INDEX
    Explanations

    mentions of journalists

    oai_token-act-pair · gpt-3.5-turbo

    references to journalists and their experiences, particularly in relation to dangers and persecution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.74
    ergy
    -0.73
    plet
    -0.70
    oku
    -0.70
    ston
    -0.66
    ascar
    -0.66
    ensions
    -0.65
    road
    -0.64
    rex
    -0.64
    ggie
    -0.63
    POSITIVE LOGITS
     journalists
    1.14
     Journalists
    1.08
     journalist
    0.88
     Journalism
    0.83
     photographers
    0.82
     reporters
    0.81
    Journal
    0.78
     laureate
    0.78
     corps
    0.77
     Seym
    0.76
    Activations Density 0.016%

    No Known Activations