© 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. 12711
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or position

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" used in various contexts throughout the text

    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
    CLASSIFIED
    -0.72
    llor
    -0.70
    NOW
    -0.64
     showc
    -0.63
     ende
    -0.63
    CVE
    -0.62
    PIN
    -0.62
     contag
    -0.60
     endors
    -0.60
     convol
    -0.59
    POSITIVE LOGITS
     lieu
    1.32
    ordinate
    1.28
    clus
    1.26
     accordance
    1.23
    animate
    1.18
     conjunction
    1.17
     vitro
    1.14
    clusions
    1.12
    patient
    1.11
    roads
    1.11
    Activations Density 0.887%

    No Known Activations