Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 9765
    Prev
    Next
    INDEX
    Explanations

    mentions of military airstrikes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military air operations

    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
     CFR
    -0.69
     Argon
    -0.68
    ANC
    -0.67
    hood
    -0.65
     Boh
    -0.65
    NC
    -0.65
    Virgin
    -0.65
     Quadro
    -0.65
    Ren
    -0.63
     Ver
    -0.63
    POSITIVE LOGITS
     airstrikes
    1.19
     raids
    1.09
     bombing
    1.05
     airstrike
    1.04
     strikes
    0.95
    querque
    0.94
     raid
    0.88
     bombings
    0.87
     bombed
    0.82
     targeting
    0.82
    Activations Density 0.017%

    No Known Activations