© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19662
    Prev
    Next
    INDEX
    Explanations

    words that include the stem "appro"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "approach" and related terms or contexts demonstrating approaches to various situations or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muller
    -0.69
     Sail
    -0.69
     Bard
    -0.68
     Tale
    -0.68
    UAL
    -0.67
    alam
    -0.65
     boats
    -0.65
     Emir
    -0.64
     Oy
    -0.63
    mouth
    -0.63
    POSITIVE LOGITS
    pton
    0.98
    ¹
    0.95
    venge
    0.88
    ached
    0.86
    ven
    0.85
    ¥ŀ
    0.82
    Ľ
    0.81
    ACTED
    0.81
    ritten
    0.80
    vised
    0.79
    Activations Density 0.018%

    No Known Activations