© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7143
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers (DOIs) in scientific references

    oai_token-act-pair · gpt-3.5-turbo

    citations and references in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crews
    -0.66
     Tray
    -0.63
     Restaur
    -0.63
     complaining
    -0.63
     revenge
    -0.61
     decor
    -0.61
    steen
    -0.61
     Polk
    -0.61
     Fired
    -0.60
    odka
    -0.60
    POSITIVE LOGITS
    doi
    1.45
     DOI
    1.37
     doi
    1.36
     PubMed
    1.11
    Abstract
    1.07
     pdf
    1.05
     Neuroscience
    0.96
    dx
    0.95
     CrossRef
    0.95
     dx
    0.93
    Activations Density 0.077%

    No Known Activations