© 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. 17321
    Prev
    Next
    INDEX
    Explanations

    phrases related to endangered or threatened species

    oai_token-act-pair · gpt-3.5-turbo

    references to endangered species and threats to their survival

    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
    ounced
    -0.80
    ibur
    -0.71
    rack
    -0.70
    ounce
    -0.69
    ahon
    -0.67
    adin
    -0.67
     brim
    -0.66
    abal
    -0.66
    aber
    -0.65
    akeru
    -0.65
    POSITIVE LOGITS
     Species
    1.12
     species
    1.07
     habitat
    0.98
     wildlife
    0.96
    species
    0.95
     endangered
    0.83
     habitats
    0.81
     elephants
    0.80
     Conservation
    0.79
    angered
    0.79
    Activations Density 0.020%

    No Known Activations