© 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. 11-RES-JB
    11. 22469
    Prev
    Next
    INDEX
    Explanations

    information related to natural disasters and their consequences

    oai_token-act-pair · gpt-3.5-turbo

    information about significant seismic events and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allowances
    -0.89
    posts
    -0.87
     guides
    -0.86
     textbooks
    -0.86
     quotas
    -0.85
     directories
    -0.85
    boards
    -0.84
    adders
    -0.82
     philosophies
    -0.82
     desks
    -0.81
    POSITIVE LOGITS
     eruption
    1.57
     event
    1.53
     earthquake
    1.53
     catastrophe
    1.53
     explosion
    1.52
     quake
    1.44
     occurrence
    1.43
     outburst
    1.39
     outbreak
    1.38
     incident
    1.38
    Activations Density 0.417%

    No Known Activations