© 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. 9-RES-JB
    11. 4755
    Prev
    Next
    INDEX
    Explanations

    Russian words

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols from a language or encoding system

    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
     traff
    -0.81
    illary
    -0.77
     GOODMAN
    -0.71
     athlet
    -0.66
     negotiator
    -0.65
    ifact
    -0.65
     stake
    -0.64
    doms
    -0.63
    emort
    -0.63
     guide
    -0.63
    POSITIVE LOGITS
    н
    1.07
    ãĤ§
    1.04
    д
    0.99
    Ñı
    0.98
    в
    0.98
    ر
    0.98
    к
    0.96
    اØ
    0.96
    ÙĨ
    0.96
    ÑĤ
    0.96
    Activations Density 0.021%

    No Known Activations