© 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. 7-RES-JB
    11. 8703
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating possession ('their', 'his', 'her') followed by words related to personal characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to possession and identity related to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    021
    -0.64
    renheit
    -0.63
     Seym
    -0.62
    0001
    -0.55
    emale
    -0.52
     Fern
    -0.50
    dn
    -0.50
    Central
    -0.50
    vu
    -0.49
     Vaugh
    -0.49
    POSITIVE LOGITS
    Ĥİ
    0.62
     Xperia
    0.62
     own
    0.60
    self
    0.57
     releases
    0.57
    zbollah
    0.56
     senses
    0.51
     release
    0.50
     sleeves
    0.50
     intended
    0.50
    Activations Density 0.248%

    No Known Activations