© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6587
    Prev
    Next
    INDEX
    Explanations

    references to outdoor natural environments, specifically focusing on 'woods'

    oai_token-act-pair · gpt-3.5-turbo

    references to wooded areas and wilderness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ihad
    -0.73
    plate
    -0.70
    ID
    -0.67
    IP
    -0.66
    Di
    -0.65
    "]=>
    -0.64
    birth
    -0.64
    Hit
    -0.64
     Dia
    -0.63
    ito
    -0.62
    POSITIVE LOGITS
     woods
    3.75
    woods
    1.92
     woodland
    1.87
     forests
    1.84
     wilderness
    1.79
     forest
    1.68
     bushes
    1.61
     Woods
    1.60
     wood
    1.54
     countryside
    1.50
    Activations Density 0.017%

    No Known Activations