© 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. 4-RES-JB
    11. 655
    Prev
    Next
    INDEX
    Explanations

    mentions of high-ranking or significant figures, places, or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "arch" in various contexts

    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
    Ô
    -0.92
    arettes
    -0.85
    uana
    -0.84
    leneck
    -0.74
    ORTS
    -0.71
    ña
    -0.71
    zzle
    -0.71
     ABE
    -0.64
    asley
    -0.64
    ACTION
    -0.64
    POSITIVE LOGITS
    bishop
    1.01
     arch
    0.98
    ipel
    0.96
    rival
    0.81
    itect
    0.78
    ival
    0.78
     nem
    0.76
    hum
    0.75
    ivist
    0.75
    di
    0.75
    Activations Density 0.005%

    No Known Activations