© 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. 4-RES-JB
    11. 14500
    Prev
    Next
    INDEX
    Explanations

    words related to natural landscapes, particularly wilderness settings

    oai_token-act-pair · gpt-3.5-turbo

    references to wilderness and wooded areas

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

    No Comments

    Negative Logits
    activation
    -0.77
    chio
    -0.75
    odor
    -0.72
    ongyang
    -0.70
    poral
    -0.67
    abolic
    -0.67
    Companies
    -0.65
    Parent
    -0.63
     differential
    -0.63
    ysis
    -0.63
    POSITIVE LOGITS
    hed
    0.93
     woodland
    0.93
     wilderness
    0.90
    erness
    0.89
    leigh
    0.89
     Wilderness
    0.88
     wasteland
    0.81
    lake
    0.80
     woods
    0.78
    dale
    0.78
    Activations Density 0.023%

    No Known Activations