© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22247
    Prev
    Next
    INDEX
    Explanations

    information about events or activities beginning or starting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "opens."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILY
    -0.77
     distress
    -0.59
     judicial
    -0.58
     debt
    -0.57
     feud
    -0.57
     subsistence
    -0.56
    OTAL
    -0.56
    reporting
    -0.55
    athered
    -0.55
    ictional
    -0.54
    POSITIVE LOGITS
     opens
    3.45
    opens
    2.51
     closes
    2.07
     opened
    2.04
     open
    1.63
     Opening
    1.60
     OPEN
    1.59
     opening
    1.57
     shuts
    1.54
    open
    1.50
    Activations Density 0.010%

    No Known Activations