© 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. 0-RES-JB
    11. 20075
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Israel

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Israel or Israeli entities

    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
     Fowler
    -0.72
     Cunning
    -0.71
     {{
    -0.69
    yth
    -0.69
    fy
    -0.64
    VOL
    -0.63
    buck
    -0.63
    ngth
    -0.63
    ynthesis
    -0.62
    swick
    -0.62
    POSITIVE LOGITS
     Israeli
    3.56
    Israeli
    3.24
     Israelis
    3.00
     Israel
    2.66
    Israel
    2.57
     IDF
    2.56
     Palestinian
    2.42
     Zionist
    2.32
    Palestinian
    2.27
     Palestinians
    2.21
    Activations Density 0.014%

    No Known Activations