© 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. 8-RES-JB
    11. 23923
    Prev
    Next
    INDEX
    Explanations

    verbs associated with preparing or paving the way for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating changes or transitions in circumstances or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uriel
    -0.65
     Catholicism
    -0.64
     weddings
    -0.60
    arians
    -0.60
    CTV
    -0.59
    manship
    -0.58
     Patron
    -0.58
    watching
    -0.55
     since
    -0.55
     Buddhism
    -0.55
    POSITIVE LOGITS
     gap
    0.84
     way
    0.82
     ground
    0.77
    circ
    0.76
     flood
    0.75
     path
    0.74
     pathway
    0.73
     gaps
    0.73
     fuse
    0.73
    ocious
    0.72
    Activations Density 0.113%

    No Known Activations