© 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. 6-RES-JB
    11. 14927
    Prev
    Next
    INDEX
    Explanations

    phrases related to different levels of expertise or suitability for specific groups of people

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating inclusivity or suitability for a broad audience

    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
     Moff
    -0.67
    shadow
    -0.65
    forward
    -0.63
    cknow
    -0.60
    inventoryQuantity
    -0.59
     brisk
    -0.58
    ãģĨ
    -0.58
     Parenthood
    -0.57
     slurs
    -0.57
     Reverend
    -0.57
    POSITIVE LOGITS
     sake
    0.88
     wishing
    0.87
     wanting
    0.83
     purposes
    0.79
     alike
    0.79
    opausal
    0.78
     adventurous
    0.78
    erning
    0.77
     aspiring
    0.77
     who
    0.76
    Activations Density 0.263%

    No Known Activations