© 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. 443
    Prev
    Next
    INDEX
    Explanations

    words starting with "encro" and "clut"

    oai_token-act-pair · gpt-4-turbo

    words related to encroachment or invasion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to infringement or encroachment on personal and collective freedoms

    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
    EStream
    -0.95
    anwhile
    -0.80
    DragonMagazine
    -0.79
    HUD
    -0.76
    hov
    -0.71
    Bloomberg
    -0.71
    REDACTED
    -0.70
    76561
    -0.70
    LECT
    -0.70
    FU
    -0.70
    POSITIVE LOGITS
    isf
    0.77
    ime
    0.76
    isd
    0.76
    arks
    0.76
    otes
    0.75
    asio
    0.74
    imes
    0.72
     arrang
    0.72
    odes
    0.71
     unnatural
    0.71
    Activations Density 0.028%

    No Known Activations