© 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. 16845
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental erosion, its consequences, and possible solutions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to soil erosion

    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
    antes
    -0.92
    erent
    -0.88
    ioned
    -0.85
    nexus
    -0.82
    ako
    -0.82
    express
    -0.82
    ulent
    -0.81
    daq
    -0.80
    ante
    -0.76
     Parables
    -0.75
    POSITIVE LOGITS
     erosion
    1.15
     eroded
    0.82
     McMaster
    0.82
     retention
    0.75
     stewards
    0.74
    issance
    0.70
     Farrell
    0.68
     inhibitors
    0.67
     priv
    0.66
     conservation
    0.65
    Activations Density 0.020%

    No Known Activations