© 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
    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. 2708
    Prev
    Next
    INDEX
    Explanations

    program or programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "pl"

    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
    âĸ¬âĸ¬
    -0.63
     managerial
    -0.61
     Logged
    -0.61
    âĸ¬
    -0.60
    MI
    -0.60
    DEM
    -0.58
     Thousand
    -0.57
     Prof
    -0.56
     politically
    -0.56
    ³³³³³³³³³³³³³³³³
    -0.54
    POSITIVE LOGITS
    acement
    1.26
    asma
    1.25
    enty
    1.24
    ains
    1.18
    osion
    1.18
    oit
    1.17
    umbing
    1.15
    icable
    1.13
    icably
    1.12
    atinum
    1.10
    Activations Density 0.021%

    No Known Activations