© 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. 4-RES-JB
    11. 16669
    Prev
    Next
    INDEX
    Explanations

    words related to strength, resilience, and fortification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fortification and defense

    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
    hner
    -0.76
    VIDEO
    -0.74
     Spectrum
    -0.73
    GROUP
    -0.71
    çīĪ
    -0.71
     Unlimited
    -0.70
     Regulatory
    -0.70
     VID
    -0.69
    lihood
    -0.69
    Gene
    -0.68
    POSITIVE LOGITS
    uitous
    1.70
    ieth
    1.33
    ifications
    1.27
    ification
    1.17
    resses
    1.15
     fort
    1.15
    itude
    1.10
    ifying
    1.05
    ified
    0.99
    itial
    0.98
    Activations Density 0.013%

    No Known Activations