Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 23045
    Prev
    Next
    INDEX
    Explanations

    mentions of family members such as husband, wife, daughter, son, boyfriend, and girlfriend in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auri
    -0.77
    arnaev
    -0.69
    etting
    -0.68
     ceilings
    -0.68
     sidx
    -0.67
    uers
    -0.67
    ãĤ¤ãĥĪ
    -0.67
    afort
    -0.65
    ãĤ¯
    -0.64
    idelines
    -0.63
    POSITIVE LOGITS
     Sandwich
    0.75
    oshop
    0.72
     todd
    0.71
    ma
    0.71
    mie
    0.68
    ÃŃs
    0.68
     hooked
    0.67
    loo
    0.67
    friend
    0.66
    my
    0.65
    Activations Density 0.090%

    No Known Activations