© 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. 8-RES-JB
    11. 8411
    Prev
    Next
    INDEX
    Explanations

    positive feedback ratings or reviews

    oai_token-act-pair · gpt-3.5-turbo

    ratings and feedback related to products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osaurus
    -0.79
    otin
    -0.74
     Frie
    -0.72
    geist
    -0.69
    soDeliveryDate
    -0.69
     Samar
    -0.67
    eming
    -0.67
    omen
    -0.65
     Dying
    -0.63
     Confeder
    -0.62
    POSITIVE LOGITS
    ãħĭ
    0.92
    ł
    0.84
    Ļ½
    0.79
    Ĺ
    0.79
     [+
    0.76
    ª
    0.72
    Posted
    0.72
    ãħĭãħĭ
    0.70
    âĺħâĺħ
    0.69
    ?????-
    0.69
    Activations Density 0.024%

    No Known Activations