© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23283
    Prev
    Next
    INDEX
    Explanations

    non-English words and terms

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters or characters that resemble words, likely in a non-standard or unconventional format

    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
     CLSID
    -0.56
     conclud
    -0.52
     referen
    -0.51
     pooled
    -0.47
     subscript
    -0.47
    Orderable
    -0.44
     corrid
    -0.44
     warranties
    -0.43
    ¿½
    -0.43
     denomin
    -0.42
    POSITIVE LOGITS
    hens
    0.57
    ensis
    0.57
    aii
    0.56
    enges
    0.52
    ng
    0.52
    atl
    0.52
    aten
    0.52
    nir
    0.52
    jee
    0.50
    ®
    0.49
    Activations Density 1.684%

    No Known Activations