© 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. 2-RES-JB
    11. 24065
    Prev
    Next
    INDEX
    Explanations

    words related to natural disasters, specifically Hurricane Katrina

    oai_token-act-pair · gpt-3.5-turbo

    references to significant disasters and historical events

    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
    Assembly
    -0.82
    lass
    -0.77
    edom
    -0.71
    ouver
    -0.70
    FTWARE
    -0.68
    techn
    -0.68
    ener
    -0.65
    Hunt
    -0.64
    Rh
    -0.64
    odox
    -0.64
    POSITIVE LOGITS
     Bagg
    0.71
     horr
    0.69
     MAP
    0.66
     Shelter
    0.66
    schild
    0.63
    arium
    0.63
     1945
    0.63
    ITE
    0.62
    gall
    0.61
    amara
    0.61
    Activations Density 0.017%

    No Known Activations