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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4490
    Prev
    Next
    INDEX
    Explanations

    special characters like symbols and letters from a non-Latin alphabet

    oai_token-act-pair · gpt-3.5-turbo

    the character "ľ" in the document

    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
    matically
    -0.77
    matic
    -0.77
    ulative
    -0.74
    anguage
    -0.74
     primates
    -0.71
    orial
    -0.71
    igators
    -0.68
    opian
    -0.67
    glomer
    -0.67
    itutional
    -0.66
    POSITIVE LOGITS
    âĶĢâĶĢ
    0.98
    xt
    0.83
    âķIJâķIJ
    0.78
    è¡
    0.77
    âĵĺ
    0.77
    ãĥĩãĤ£
    0.76
    ×Ķ
    0.76
    STER
    0.74
    LEASE
    0.73
    å§«
    0.72
    Activations Density 0.029%

    No Known Activations