© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 16429
    Prev
    Next
    INDEX
    Explanations

    specific names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly related to specific individuals or entities

    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
     palms
    -0.67
     beacon
    -0.67
    nect
    -0.67
    pers
    -0.66
    figure
    -0.64
     Canary
    -0.61
     brace
    -0.60
     loyalty
    -0.59
     perspect
    -0.59
    liction
    -0.58
    POSITIVE LOGITS
    loo
    1.19
    icz
    0.90
    riv
    0.89
    kj
    0.86
    atical
    0.84
    ially
    0.84
    itives
    0.83
    PLIC
    0.83
    andom
    0.83
    anium
    0.82
    Activations Density 0.015%

    No Known Activations