© 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. 3-RES-JB
    11. 2926
    Prev
    Next
    INDEX
    Explanations

    specific events or situations

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns or terms related to policy and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.63
    thood
    -0.63
    DonaldTrump
    -0.62
    itored
    -0.59
    $.
    -0.58
    Lago
    -0.58
    omever
    -0.57
    +.
    -0.57
    ãģ¾
    -0.57
    idelity
    -0.56
    POSITIVE LOGITS
     consists
    0.54
    iest
    0.54
     grate
    0.54
     consisted
    0.52
     question
    0.52
     brist
    0.51
     dilemma
    0.50
     succeeded
    0.50
     NETWORK
    0.49
     also
    0.49
    Activations Density 1.488%

    No Known Activations