© 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. 15790
    Prev
    Next
    INDEX
    Explanations

    colors in a multi-colored format

    oai_token-act-pair · gpt-3.5-turbo

    terms related to colors and the word "Nicol."

    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
    Reply
    -0.78
     Cosponsors
    -0.71
    JECT
    -0.68
    CHA
    -0.66
     backlog
    -0.66
    QUEST
    -0.66
    ourke
    -0.65
    Eva
    -0.65
     mitigation
    -0.62
     Defenders
    -0.62
    POSITIVE LOGITS
    icol
    1.32
    umbered
    1.03
    ás
    1.01
    oresc
    0.96
    uously
    0.93
    osph
    0.93
    umn
    0.89
    orescence
    0.89
    ancies
    0.88
    mares
    0.87
    Activations Density 0.013%

    No Known Activations