© 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. 4-RES-JB
    11. 7225
    Prev
    Next
    INDEX
    Explanations

    financial or legislative terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and proposals regarding legislative actions or consequences

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

    No Comments

    Negative Logits
     Chal
    -0.68
    Writing
    -0.67
    Pie
    -0.66
    Ti
    -0.66
     Tuc
    -0.65
     Paran
    -0.65
     Corpus
    -0.64
     Sung
    -0.64
     Velocity
    -0.62
     Xuan
    -0.61
    POSITIVE LOGITS
     be
    1.03
     doubtless
    1.02
     undoubtedly
    0.98
     likely
    0.95
     surely
    0.93
     introduce
    0.90
     inevitably
    0.89
     probably
    0.89
     imply
    0.88
     eliminate
    0.87
    Activations Density 0.148%

    No Known Activations