© 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. 20941
    Prev
    Next
    INDEX
    Explanations

    patterns related to electrical connections and procedures

    oai_token-act-pair · gpt-3.5-turbo

    connections and relationships between components in a technical or instructional context

    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
    SPONSORED
    -0.93
    âĢİ
    -0.87
    Bloomberg
    -0.71
    tackle
    -0.71
     âĢº
    -0.68
    /
    -0.68
    CLASSIFIED
    -0.65
     Damian
    -0.65
     Jamal
    -0.63
     Maher
    -0.62
    POSITIVE LOGITS
     entire
    1.26
     same
    1.25
     entirety
    1.24
     remainder
    1.23
     smallest
    1.21
     latter
    1.20
     aforementioned
    1.19
     simplest
    1.16
     slightest
    1.14
     nearest
    1.14
    Activations Density 1.653%

    No Known Activations