© 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. 2-RES-JB
    11. 10391
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Col" and its variations, indicating references to institutions or locations associated with that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Werewolf
    -0.86
     forth
    -0.76
    natureconservancy
    -0.74
    DragonMagazine
    -0.73
     Remastered
    -0.72
    cffffcc
    -0.72
    visor
    -0.67
     Potential
    -0.67
    VALUE
    -0.65
     WHO
    -0.64
    POSITIVE LOGITS
    ossal
    1.16
    ombo
    1.03
    onial
    0.97
    onel
    0.96
    umbo
    0.94
    leen
    0.94
    ours
    0.94
    lections
    0.92
    icol
    0.92
    ophon
    0.90
    Activations Density 0.005%

    No Known Activations