© 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. 20615
    Prev
    Next
    INDEX
    Explanations

    determiners and conjoined words

    oai_token-act-pair · gpt-3.5-turbo

    references to questioning, beliefs, and the implications of actions

    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
     lately
    -0.72
    DX
    -0.67
    jen
    -0.67
    uncture
    -0.56
    inventoryQuantity
    -0.56
     craw
    -0.56
    lies
    -0.56
    FTWARE
    -0.55
    tains
    -0.54
     latest
    -0.54
    POSITIVE LOGITS
    would
    1.99
     would
    1.88
     Would
    1.73
     wouldn
    1.68
    Would
    1.59
     Wouldn
    1.49
    could
    1.29
    'd
    1.25
     could
    1.19
    OULD
    1.18
    Activations Density 0.838%

    No Known Activations