© 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. 1385
    Prev
    Next
    INDEX
    Explanations

    instances of the word "family"

    oai_token-act-pair · gpt-3.5-turbo

    words expressing intensity of emotion or conditions associated with feelings

    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
     Riders
    -0.73
    href
    -0.71
     Avalon
    -0.69
    raviolet
    -0.67
     Settlement
    -0.63
     Apostles
    -0.63
    afety
    -0.62
     Canary
    -0.62
     receivers
    -0.61
     Zero
    -0.60
    POSITIVE LOGITS
    mph
    0.86
    yy
    0.86
    ily
    0.85
    adow
    0.77
    zed
    0.75
    clad
    0.75
    ãĤ©
    0.75
    flies
    0.73
    pha
    0.73
    acies
    0.71
    Activations Density 0.013%

    No Known Activations