© 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. 22178
    Prev
    Next
    INDEX
    Explanations

    words related to natural habitats and conservation

    oai_token-act-pair · gpt-3.5-turbo

    references to habitat in various contexts

    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
    ivan
    -0.74
    racted
    -0.72
    agher
    -0.71
    inness
    -0.70
    ining
    -0.69
    ochet
    -0.67
    ahon
    -0.67
    ripp
    -0.65
    uggage
    -0.65
    Roy
    -0.64
    POSITIVE LOGITS
     habitat
    1.23
     habitats
    1.07
    conservancy
    0.90
     dwell
    0.85
     ecosystems
    0.79
     dwelling
    0.78
     enclosure
    0.76
     encl
    0.74
     ecology
    0.72
     vegetation
    0.71
    Activations Density 0.008%

    No Known Activations