© 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. 4-RES-JB
    11. 14831
    Prev
    Next
    INDEX
    Explanations

    ecosystem-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    elements related to biodiversity and ecosystems

    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
    --------------------------------------------------------
    -0.82
    ZI
    -0.81
    advertising
    -0.73
    iaz
    -0.68
    zos
    -0.67
     pistols
    -0.67
    HK
    -0.66
     handcuffs
    -0.65
    ochet
    -0.64
     satirical
    -0.64
    POSITIVE LOGITS
     biodiversity
    1.17
     habitat
    1.13
     habitats
    1.10
     vegetation
    1.10
     flora
    1.09
     ecology
    1.05
     ecosystems
    1.00
    rients
    0.99
     gardens
    0.97
     richness
    0.92
    Activations Density 0.141%

    No Known Activations