© 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
    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. 19853
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or research settings, particularly in the context of conservation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental preservation or conservation

    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
    illes
    -0.79
     partName
    -0.77
    _-_
    -0.71
     Glas
    -0.71
     Trees
    -0.70
    ¨
    -0.70
    closed
    -0.70
    olin
    -0.68
    odox
    -0.68
     guiActiveUnfocused
    -0.67
    POSITIVE LOGITS
     paternity
    0.77
    itan
    0.75
     Californ
    0.69
     fertility
    0.67
     Kimmel
    0.67
     idiots
    0.66
     iodine
    0.66
     moms
    0.65
     Democrats
    0.63
     dads
    0.62
    Activations Density 0.000%

    No Known Activations