© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 19306
    Prev
    Next
    INDEX
    Explanations

    information related to sea level rise and its impacts

    oai_token-act-pair · gpt-3.5-turbo

    references to sea level rise and related environmental concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILY
    -0.82
    YN
    -0.76
    vell
    -0.75
    imental
    -0.74
    lez
    -0.74
    blance
    -0.74
    Animal
    -0.74
    spective
    -0.72
    vous
    -0.71
    ouri
    -0.70
    POSITIVE LOGITS
     crossings
    0.85
     dams
    0.85
     cliffs
    0.84
     rise
    0.84
     impacts
    0.83
     ceilings
    0.80
     sinks
    0.79
     settlement
    0.78
     Observatory
    0.78
     canopy
    0.76
    Activations Density 0.049%

    No Known Activations