© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16618
    Prev
    Next
    INDEX
    Explanations

    terms related to ecology and ecologically mindful practices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ecology and ecological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pall
    -0.68
     Colt
    -0.65
     Arcane
    -0.64
     [+
    -0.63
     Alleg
    -0.63
     repay
    -0.63
    holders
    -0.60
     REPORT
    -0.59
     karma
    -0.58
     Shinra
    -0.58
    POSITIVE LOGITS
    uador
    1.26
    stasy
    1.23
    lectic
    1.19
    umen
    1.15
    static
    1.11
    ologically
    1.05
    utive
    1.02
    entric
    0.98
    urrency
    0.97
    risis
    0.96
    Activations Density 0.036%

    No Known Activations