© 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. 3-RES-JB
    11. 5948
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that contain the word "Cor" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cor" and its variants throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.92
    lihood
    -0.90
    terday
    -0.86
    CRIP
    -0.85
     Dangerous
    -0.77
    anwhile
    -0.77
    pmwiki
    -0.77
    ï¸
    -0.76
    WARE
    -0.73
     Difficulty
    -0.73
    POSITIVE LOGITS
    rigan
    1.18
    rupt
    1.02
    relation
    1.00
    fman
    0.99
    ros
    0.97
    ruption
    0.97
    bis
    0.92
    porate
    0.91
    rupted
    0.89
    bett
    0.89
    Activations Density 0.006%

    No Known Activations