© 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. 0-RES-JB
    11. 8296
    Prev
    Next
    INDEX
    Explanations

    terms related to data collection and gathering

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "collected" in various contexts

    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
    ital
    -0.81
    î
    -0.71
    nee
    -0.71
    nik
    -0.66
    quit
    -0.65
     externalToEVAOnly
    -0.64
    ember
    -0.64
    lihood
    -0.64
    NESS
    -0.63
    ential
    -0.63
    POSITIVE LOGITS
     collected
    3.51
     collects
    2.16
     collecting
    1.95
     collect
    1.88
     gathered
    1.87
     Collect
    1.86
     collection
    1.63
     accumulated
    1.57
     amassed
    1.57
     retrieved
    1.52
    Activations Density 0.016%

    No Known Activations