© 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. 11-RES-JB
    11. 18506
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    words related to new information or developments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otal
    -0.70
    theless
    -0.63
    ower
    -0.63
    itual
    -0.61
    GG
    -0.60
    fore
    -0.59
    agi
    -0.59
     neglig
    -0.59
     spare
    -0.58
    beit
    -0.58
    POSITIVE LOGITS
     arrivals
    0.99
     additions
    0.95
     entrants
    0.88
     hires
    0.87
     addition
    0.85
     introduced
    0.84
     arrival
    0.80
     emerging
    0.79
     added
    0.79
     arriving
    0.79
    Activations Density 0.398%

    No Known Activations