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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 8436
    Prev
    Next
    INDEX
    Explanations

    phrases related to family connections such as son-in-law, brother, and marriage

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating familial relationships, specifically related to sons-in-law

    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
    ORTS
    -0.66
    eatures
    -0.64
     pressures
    -0.63
    houn
    -0.63
    cliffe
    -0.62
    dq
    -0.61
    earcher
    -0.60
    essor
    -0.59
    WT
    -0.59
    )].
    -0.59
    POSITIVE LOGITS
    rette
    0.63
     Jol
    0.61
    umeric
    0.61
     Gaul
    0.60
    wered
    0.60
     Asc
    0.59
    Sax
    0.59
    opter
    0.58
    ault
    0.57
     Odin
    0.56
    Activations Density 0.318%

    No Known Activations