© 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. 2-RES-JB
    11. 12980
    Prev
    Next
    INDEX
    Explanations

    Russian Cyrillic characters, possibly related to text encoding

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "о" and similar Cyrillic characters

    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
     Clover
    -0.92
    esville
    -0.85
    hyde
    -0.79
    ologically
    -0.79
    secut
    -0.73
    ometimes
    -0.72
    raints
    -0.71
    eele
    -0.69
    irable
    -0.69
     Ada
    -0.69
    POSITIVE LOGITS
    Ñ
    1.21
    ÑĢ
    1.18
    е
    1.18
    н
    1.14
    ÑĤ
    1.13
    Ñģ
    1.11
    о
    1.09
    и
    1.04
     Ð
    1.01
    Ñı
    1.00
    Activations Density 0.003%

    No Known Activations