© 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. 2-RES-JB
    11. 17535
    Prev
    Next
    INDEX
    Explanations

    references to environmental conditions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "elements" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.83
    Stra
    -0.68
    rontal
    -0.65
    raid
    -0.63
    lishing
    -0.63
    BI
    -0.62
    redo
    -0.62
    Pitt
    -0.61
    take
    -0.61
    Bull
    -0.61
    POSITIVE LOGITS
     elements
    1.40
     element
    1.18
     guiActiveUn
    0.81
    osaurs
    0.78
     components
    0.77
    icides
    0.76
     layers
    0.76
     Elements
    0.76
    tones
    0.75
    aea
    0.75
    Activations Density 0.012%

    No Known Activations