© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 9736
    Prev
    Next
    INDEX
    Explanations

    phrases related to making fun of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ridicule or making fun of someone or something

    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
    taboola
    -0.75
    cci
    -0.71
    aird
    -0.70
    ickr
    -0.69
    rang
    -0.68
    externalActionCode
    -0.68
    hig
    -0.65
    aucas
    -0.65
    ivities
    -0.64
    isSpecialOrderable
    -0.64
    POSITIVE LOGITS
     yourselves
    0.85
     ourselves
    0.82
     yourself
    0.78
     himself
    0.72
     whatever
    0.68
     these
    0.66
     oneself
    0.66
    erous
    0.65
     Yourself
    0.65
     Himself
    0.65
    Activations Density 0.331%

    No Known Activations