© 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. 9831
    Prev
    Next
    INDEX
    Explanations

    terms related to explosions or destruction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to explosions and tearing apart

    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
    BIL
    -0.79
    eele
    -0.76
    00200000
    -0.71
    Released
    -0.70
    OIL
    -0.70
    uckland
    -0.67
    uga
    -0.67
    illus
    -0.66
    reon
    -0.66
    addon
    -0.66
    POSITIVE LOGITS
     havoc
    0.95
     bridges
    0.82
     asphalt
    0.71
     tires
    0.71
     roy
    0.69
     miser
    0.68
     laughing
    0.67
     Nebula
    0.65
     747
    0.64
    adoes
    0.63
    Activations Density 0.110%

    No Known Activations