© 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. 16835
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "our"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "our"

    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
     revert
    -0.64
    minster
    -0.63
     buck
    -0.62
    FU
    -0.61
     Tanz
    -0.59
     citation
    -0.58
     Rasmussen
    -0.57
     stem
    -0.57
     mesh
    -0.57
     rusher
    -0.56
    POSITIVE LOGITS
    our
    1.25
    selves
    1.24
    neau
    1.01
    neys
    1.00
    ours
    0.94
    ¯¯¯¯¯¯¯¯
    0.89
    OUR
    0.86
    izont
    0.86
    ouring
    0.85
    oux
    0.81
    Activations Density 0.010%

    No Known Activations