© 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. 4-RES-JB
    11. 22094
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to individuals, particularly those involved in politics or notable events

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

    No Comments

    Negative Logits
    izable
    -0.77
    izing
    -0.75
    ifiable
    -0.72
    ising
    -0.71
    eness
    -0.71
    itudes
    -0.70
    ified
    -0.68
    ized
    -0.67
    izes
    -0.67
    ured
    -0.65
    POSITIVE LOGITS
    vernment
    0.83
    ringe
    0.83
    izons
    0.82
    ritz
    0.79
    zzle
    0.78
    ellow
    0.77
    izontal
    0.77
    rian
    0.77
    avorite
    0.73
    rost
    0.73
    Activations Density 0.037%

    No Known Activations