© 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. 4-RES-JB
    11. 734
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or terms

    oai_token-act-pair · gpt-3.5-turbo

    proper names of people, particularly those involved in sports or entertainment

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

    No Comments

    Negative Logits
    ovych
    -0.88
    dfx
    -0.78
    CLASS
    -0.70
    #$
    -0.64
     gobl
    -0.62
    POSE
    -0.61
    ¯
    -0.60
     reckoning
    -0.59
    PASS
    -0.59
    oppable
    -0.59
    POSITIVE LOGITS
    xus
    0.89
    igham
    0.86
    eros
    0.80
    cius
    0.78
    oglu
    0.77
    antes
    0.76
    ortium
    0.73
    abre
    0.70
    ople
    0.70
    loe
    0.70
    Activations Density 0.332%

    No Known Activations