© 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. 6574
    Prev
    Next
    INDEX
    Explanations

    terms related to movement from one place to another, often involving travel or transportation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "en-" indicating ongoing action or state

    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
    ij士
    -0.67
     independently
    -0.63
     Palmer
    -0.60
     overdue
    -0.60
     Intermediate
    -0.60
     Pell
    -0.57
     reconc
    -0.56
     Pyth
    -0.55
     behind
    -0.55
     Davidson
    -0.54
    POSITIVE LOGITS
    viron
    1.30
    igma
    1.18
     masse
    1.17
    unci
    1.15
    forcer
    1.14
    amel
    1.13
    cyclop
    1.12
    joined
    1.07
    quire
    1.07
    route
    1.06
    Activations Density 0.013%

    No Known Activations