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

    Neuronpedia

    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. 10400
    Prev
    Next
    INDEX
    Explanations

    words related to the programming language Lisp

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ISP."

    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
     Valent
    -0.67
     Biblical
    -0.67
     bear
    -0.66
    DER
    -0.64
     Idol
    -0.64
     Bundy
    -0.64
     Greenwich
    -0.63
     Apostles
    -0.63
    tty
    -0.61
     centimeters
    -0.61
    POSITIVE LOGITS
    ensable
    1.06
    isp
    1.04
    olitics
    1.02
    ionage
    0.98
    olicy
    0.98
    heric
    0.95
    irit
    0.91
    ipeg
    0.87
    aque
    0.86
    rax
    0.86
    Activations Density 0.007%

    No Known Activations