© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17774
    Prev
    Next
    INDEX
    Explanations

    names that start or end with "Nik"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the name "Nik" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cellular
    -0.76
    dress
    -0.70
    heads
    -0.66
    pants
    -0.66
    ordinary
    -0.65
     marrow
    -0.65
     Gaga
    -0.64
     mainland
    -0.64
     STEM
    -0.64
     bast
    -0.63
    POSITIVE LOGITS
    aido
    1.24
    ita
    1.05
    umar
    1.03
    opol
    1.03
    olas
    0.97
    kie
    0.96
    Ĺ
    0.95
    Ŀ
    0.94
    ols
    0.92
    elsen
    0.92
    Activations Density 0.041%

    No Known Activations