© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 17262
    Prev
    Next
    INDEX
    Explanations

    pronouns or nouns referring to people or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional states and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.89
    ritz
    -0.78
    raltar
    -0.76
    Ń·
    -0.76
    nsic
    -0.74
    nown
    -0.74
    ĸļ
    -0.73
    ilaterally
    -0.72
    ftime
    -0.71
    «ĺ
    -0.70
    POSITIVE LOGITS
    athe
    0.69
     awaited
    0.69
     Yor
    0.60
     newsp
    0.59
     Sear
    0.57
     Droid
    0.57
     depends
    0.56
     Protoss
    0.56
     affair
    0.56
     breaths
    0.55
    Activations Density 0.086%

    No Known Activations