© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    Twitter handles and usernames

    oai_token-act-pair · gpt-3.5-turbo

    identifiers or handles associated with social media profiles

    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
    theless
    -0.76
     CPI
    -0.69
    illary
    -0.64
     fingert
    -0.63
    wcsstore
    -0.61
     substitutes
    -0.61
    ========
    -0.60
    ÄŁ
    -0.60
     rejoice
    -0.57
    inventoryQuantity
    -0.57
    POSITIVE LOGITS
    dq
    0.78
    dn
    0.76
    rique
    0.71
    tt
    0.70
    bt
    0.70
    vP
    0.70
    XM
    0.68
    Q
    0.68
    ibrary
    0.67
    cham
    0.67
    Activations Density 0.106%

    No Known Activations