© 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. 1-RES-JB
    11. 13357
    Prev
    Next
    INDEX
    Explanations

    phrases related to placement or assignment of people or things

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "placed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -1.13
    bie
    -0.86
    vous
    -0.76
    bi
    -0.72
    core
    -0.67
    Prin
    -0.65
    ses
    -0.65
    RESULTS
    -0.64
    rd
    -0.63
    lic
    -0.63
    POSITIVE LOGITS
     satell
    0.99
     veter
    0.96
    arnaev
    0.95
     placed
    0.93
     placing
    0.91
     toget
    0.90
    VIDIA
    0.88
     Parenthood
    0.87
     showc
    0.86
    everal
    0.86
    Activations Density 0.011%

    No Known Activations