© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1073
    Prev
    Next
    INDEX
    Explanations

    Russian words containing the letter combination "к"

    oai_token-act-pair · gpt-3.5-turbo

    words related to sacrificial themes and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xon
    -0.90
    iannopoulos
    -0.81
    uana
    -0.76
    udence
    -0.75
    justice
    -0.73
     Rudd
    -0.73
    owell
    -0.73
     whistleblower
    -0.71
    ulp
    -0.70
    weed
    -0.69
    POSITIVE LOGITS
    к
    2.14
    sac
    1.86
     Sac
    1.75
    Sac
    1.73
    etts
    1.20
     Marian
    1.12
     Tet
    1.02
     beads
    1.02
     tet
    1.02
     lifelong
    1.02
    Activations Density 0.045%

    No Known Activations