© 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. 24213
    Prev
    Next
    INDEX
    Explanations

    words related to geological processes and environmental erosion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geological processes and erosion

    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
    nam
    -0.94
    figured
    -0.80
    paren
    -0.79
    oshenko
    -0.78
    nic
    -0.77
    acon
    -0.76
    digit
    -0.75
    abre
    -0.75
    acles
    -0.75
    unal
    -0.74
    POSITIVE LOGITS
     erosion
    0.95
     glaciers
    0.91
     drift
    0.80
     eroded
    0.78
     runoff
    0.76
     glacier
    0.75
     formations
    0.74
     Lauder
    0.72
     reflection
    0.71
     fracturing
    0.70
    Activations Density 0.028%

    No Known Activations