© 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. 3-RES-JB
    11. 372
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Raza" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals with the last name "Raza" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bold
    -0.80
     lips
    -0.73
    gling
    -0.71
    bon
    -0.69
    aceous
    -0.69
    ply
    -0.67
     smugg
    -0.66
    regon
    -0.65
    sole
    -0.64
    xious
    -0.64
    POSITIVE LOGITS
    eneg
    0.89
    ires
    0.85
    aza
    0.81
    ire
    0.80
    HAHAHAHA
    0.80
    inary
    0.79
    UGE
    0.77
    ired
    0.75
     Leban
    0.74
    np
    0.73
    Activations Density 0.018%

    No Known Activations