© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1494
    Prev
    Next
    INDEX
    Explanations

    words related to being benched or dismissed from a position

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ben" or related terms

    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
    CV
    -0.75
    District
    -0.74
    DragonMagazine
    -0.72
    tale
    -0.72
     Fiscal
    -0.71
    ocene
    -0.70
    matic
    -0.67
     Dispatch
    -0.66
     Mouth
    -0.66
    hips
    -0.66
    POSITIVE LOGITS
    jamin
    1.56
    ghazi
    1.00
    ificial
    0.89
    jo
    0.88
    EF
    0.86
     ben
    0.86
    nington
    0.85
    isance
    0.84
    isher
    0.79
    jam
    0.77
    Activations Density 0.008%

    No Known Activations