© 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. 2-RES-JB
    11. 12529
    Prev
    Next
    INDEX
    Explanations

    words related to names, specifically those ending with 'zel'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters named 'Zel'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raising
    -0.76
    irlf
    -0.75
    recomm
    -0.68
    ¥ŀ
    -0.68
     Palestin
    -0.68
     newsp
    -0.67
    ortunately
    -0.66
     Retirement
    -0.65
     totality
    -0.64
    rising
    -0.64
    POSITIVE LOGITS
    zel
    0.99
    baum
    0.97
    toe
    0.94
    abor
    0.93
    mann
    0.93
    wald
    0.92
    feld
    0.91
    bug
    0.91
    onne
    0.90
    nut
    0.83
    Activations Density 0.006%

    No Known Activations