© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    programming or technical instructions related to setting up email filters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various forms of regulation or compliance

    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
    ['
    -0.49
    éĹĺ
    -0.48
     duly
    -0.45
     reinstated
    -0.45
     suffice
    -0.42
     abolished
    -0.42
     exempted
    -0.42
    omever
    -0.42
    raltar
    -0.41
    umenthal
    -0.41
    POSITIVE LOGITS
     Ltd
    0.55
     Medals
    0.52
     Binary
    0.52
     Mana
    0.51
     Products
    0.51
     Simulator
    0.51
     Caps
    0.51
     Happiness
    0.50
     Decoder
    0.50
     Unit
    0.49
    Activations Density 2.044%

    No Known Activations