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

    mentions of explosive devices, particularly cluster bombs

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of bombs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SEA
    -0.83
    Relations
    -0.82
    Stud
    -0.77
    TH
    -0.75
    Days
    -0.71
    WR
    -0.71
     Orth
    -0.70
    States
    -0.70
     Malt
    -0.69
    WD
    -0.69
    POSITIVE LOGITS
     bombs
    1.17
    poons
    1.13
     detonated
    1.07
     deton
    1.02
     bombings
    0.98
     bomb
    0.95
     bomber
    0.93
     bombing
    0.93
    poon
    0.90
     bombed
    0.89
    Activations Density 0.005%

    No Known Activations