© 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. 12109
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal issues and conflicts

    oai_token-act-pair · gpt-3.5-turbo
    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
     GOODMAN
    -0.87
    oubtedly
    -0.73
    atform
    -0.69
    iameter
    -0.66
    Nav
    -0.64
    ovation
    -0.63
    ä¸Ĭ
    -0.63
     metre
    -0.63
    ktop
    -0.63
    izen
    -0.62
    POSITIVE LOGITS
     incest
    1.40
     abusive
    1.35
     adultery
    1.28
     boyfriend
    1.28
     divorce
    1.27
     raped
    1.24
     pedoph
    1.24
     blackmail
    1.24
     rapist
    1.22
     sexually
    1.21
    Activations Density 0.799%

    No Known Activations