Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2469
    Prev
    Next
    INDEX
    Explanations

    Slavic languages and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific words or phrases in a language, potentially indicating a linguistic focus or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayer
    -0.83
    arton
    -0.77
     additive
    -0.71
    ¿½
    -0.70
    onsense
    -0.66
    cause
    -0.66
    reads
    -0.65
    buquerque
    -0.64
    ACTED
    -0.64
    guyen
    -0.62
    POSITIVE LOGITS
    оÐ
    1.19
    о
    1.07
    ÑĢ
    1.07
    л
    1.03
    а
    1.00
    Ñĥ
    0.98
    и
    0.97
    в
    0.85
    ÑĤ
    0.82
    eers
    0.80
    Activations Density 0.022%

    No Known Activations