© 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. 10-RES-JB
    11. 11509
    Prev
    Next
    INDEX
    Explanations

    legal and judicial terms

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard text elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beaut
    -0.67
     handshake
    -0.65
     shroud
    -0.64
     bragging
    -0.64
     smokes
    -0.64
     tongues
    -0.63
     mate
    -0.63
     lovers
    -0.62
    ozy
    -0.61
     mans
    -0.61
    POSITIVE LOGITS
    ¡
    1.12
    ¤
    1.07
    ł
    1.05
    º
    1.01
    ²
    0.99
    µ
    0.99
    Ĵ
    0.97
    ¸
    0.97
    ¹
    0.94
    ³
    0.94
    Activations Density 0.386%

    No Known Activations