© 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. 3-RES-JB
    6. 2978
    Prev
    Next
    INDEX
    Explanations

    words related to evaluation or judgment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ratings and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amar
    -0.80
    aina
    -0.72
    auga
    -0.70
    umi
    -0.62
    aida
    -0.62
    paio
    -0.62
    SW
    -0.61
    AMI
    -0.61
     undone
    -0.61
    enger
    -0.60
    POSITIVE LOGITS
    senal
    0.90
    xual
    0.85
    ration
    0.79
    hyde
    0.78
    phrine
    0.74
    rating
    0.69
    mble
    0.68
    secution
    0.68
    zinski
    0.68
    Beer
    0.68
    Activations Density 0.020%

    No Known Activations