© 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. 3121
    Prev
    Next
    INDEX
    Explanations

    short phrases or sentences focused on specific actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation marks

    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
     tack
    -0.72
    NetMessage
    -0.72
    "?
    -0.64
     anyway
    -0.64
    .</
    -0.63
     hug
    -0.61
     ain
    -0.61
     quir
    -0.60
     suspic
    -0.60
     extinct
    -0.60
    POSITIVE LOGITS
     Whilst
    1.88
     Firstly
    1.55
     Initially
    1.48
     However
    1.38
     While
    1.36
     This
    1.35
     Although
    1.31
     These
    1.30
     During
    1.30
     Specifically
    1.29
    Activations Density 0.565%

    No Known Activations