© 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 EvalsExportsinterp-engineNEWAPI 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. 23710
    Prev
    Next
    INDEX
    Explanations

    words related to strong determination or a particular direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe determination or a strong inclination towards a goal

    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
    pedia
    -0.83
    reports
    -0.74
    pmwiki
    -0.69
    inventoryQuantity
    -0.69
    Naz
    -0.68
     Rout
    -0.67
    Downloadha
    -0.64
    åħī
    -0.64
     testimonies
    -0.63
    ä¹ĭ
    -0.63
    POSITIVE LOGITS
     bent
    0.86
    arius
    0.86
    onite
    0.85
    lass
    0.82
    wig
    0.78
    irection
    0.76
    ractor
    0.72
     squid
    0.71
    ulously
    0.71
    thro
    0.71
    Activations Density 0.015%

    No Known Activations