© 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. 0-RES-JB
    11. 15046
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events relating to potential struggle or conflict

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "t."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.79
    ylum
    -0.64
    abre
    -0.62
    skill
    -0.61
    Accessory
    -0.60
    ernels
    -0.60
     Dragonbound
    -0.60
    anca
    -0.59
    ixel
    -0.59
    igl
    -0.58
    POSITIVE LOGITS
     t
    3.05
     T
    1.56
     ts
    1.53
     tion
    1.42
     r
    1.30
     s
    1.27
     ti
    1.27
     ta
    1.26
     c
    1.25
    T
    1.25
    Activations Density 0.026%

    No Known Activations