© 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. 8-RES-JB
    11. 7616
    Prev
    Next
    INDEX
    Explanations

    information related to news, weather, and events, particularly in a local context

    oai_token-act-pair · gpt-3.5-turbo

    content related to news and current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.78
    ĸļ
    -0.76
    aterasu
    -0.70
     suffice
    -0.67
    iciency
    -0.67
    icient
    -0.66
     intermediary
    -0.66
    utor
    -0.66
    velop
    -0.64
    perture
    -0.64
    POSITIVE LOGITS
     news
    1.06
     goodies
    0.99
     trending
    0.96
     celeb
    0.92
     NEWS
    0.91
     podcasts
    0.91
    Trend
    0.88
     developments
    0.84
    scribe
    0.83
    News
    0.83
    Activations Density 0.388%

    No Known Activations