© 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. 7-RES-JB
    11. 2009
    Prev
    Next
    INDEX
    Explanations

    words related to introducing or implementing new initiatives or plans

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'new' or innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istine
    -0.78
    acebook
    -0.76
    OPA
    -0.75
    aminer
    -0.75
    UMP
    -0.72
    ocene
    -0.68
    Zip
    -0.68
    amus
    -0.66
    ouse
    -0.65
    uca
    -0.63
    POSITIVE LOGITS
    bies
    1.42
     arrivals
    1.22
    bie
    1.21
     entrants
    1.09
     additions
    1.07
     developments
    1.06
    foundland
    1.03
     discoveries
    1.02
     generations
    0.98
     hires
    0.97
    Activations Density 0.079%

    No Known Activations