© 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. 6-RES-JB
    11. 17339
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing off or dismissing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of writing something off or dismissing it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aternity
    -0.75
    cius
    -0.75
    hig
    -0.73
    rador
    -0.73
    leground
    -0.68
    iosity
    -0.67
    ushi
    -0.65
    rouse
    -0.64
    gpu
    -0.64
    taboola
    -0.63
    POSITIVE LOGITS
    antha
    0.70
     scraps
    0.69
     waivers
    0.63
    RR
    0.62
     Ness
    0.60
     existence
    0.60
    umber
    0.59
    SI
    0.58
     Tup
    0.58
    umbered
    0.58
    Activations Density 0.088%

    No Known Activations