© 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. 9421
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Og" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and characters

    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
    âĸ¬
    -0.82
    izations
    -0.76
    âķIJâķIJ
    -0.72
    ization
    -0.71
    HCR
    -0.70
    theless
    -0.67
     CPC
    -0.67
     PID
    -0.67
    terday
    -0.66
    isation
    -0.65
    POSITIVE LOGITS
    yssey
    0.98
     Og
    0.91
    regor
    0.89
    rib
    0.86
    ghan
    0.86
    oby
    0.85
    uchi
    0.84
    owan
    0.83
    arrison
    0.82
    ridge
    0.82
    Activations Density 0.011%

    No Known Activations