© 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. 0-RES-JB
    11. 1139
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or association

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities characterized by the word "whose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptions
    -0.62
    PLA
    -0.60
    rums
    -0.58
    aze
    -0.54
    eco
    -0.53
     Alright
    -0.51
    ming
    -0.51
     info
    -0.51
     Things
    -0.50
    mo
    -0.50
    POSITIVE LOGITS
     whose
    3.15
    whose
    2.68
     whom
    2.31
     who
    1.74
    who
    1.61
     whence
    1.36
     which
    1.32
     wherein
    1.17
    WHO
    1.03
    which
    1.03
    Activations Density 0.021%

    No Known Activations