© 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. 2231
    Prev
    Next
    INDEX
    Explanations

    phrases containing military ranks and names

    oai_token-act-pair · gpt-3.5-turbo

    references to military and police ranks

    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
    ahime
    -0.83
    rights
    -0.76
    theless
    -0.75
    FORE
    -0.68
    phal
    -0.65
     spoiler
    -0.64
    flix
    -0.64
    女
    -0.64
     destro
    -0.63
    GPU
    -0.63
    POSITIVE LOGITS
    geant
    1.18
     Sgt
    1.11
     Sergeant
    0.93
    gt
    0.91
     Pepper
    0.90
    veland
    0.84
     Maj
    0.82
     sergeant
    0.79
    cha
    0.77
     Clancy
    0.77
    Activations Density 0.031%

    No Known Activations