© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4573
    Prev
    Next
    INDEX
    Explanations

    phrases related to family members, especially referring to the roles of "Mom" and "Dad"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'Mom' and variations of familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.67
    chnology
    -0.65
     claimants
    -0.62
     Ferdinand
    -0.61
     Commonwealth
    -0.61
     Tribunal
    -0.60
     similarities
    -0.60
     Dull
    -0.60
     Squadron
    -0.58
     extrap
    -0.58
    POSITIVE LOGITS
    my
    1.47
    ma
    1.13
    mers
    1.09
    hesis
    1.07
    entary
    1.06
    iji
    1.01
    mer
    1.01
    MY
    0.95
    pered
    0.92
    puter
    0.90
    Activations Density 0.033%

    No Known Activations