© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 20384
    Prev
    Next
    INDEX
    Explanations

    terms related to family lineage, specifically highlighting the term "grand" along with descriptions of family relations

    oai_token-act-pair · gpt-3.5-turbo

    references to 'grand' in various contexts, particularly related to ancestry and lineage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.86
    tics
    -0.76
    ijk
    -0.70
     Alvarez
    -0.69
    uality
    -0.60
     stocks
    -0.59
     specially
    -0.59
     warranted
    -0.57
     surfaced
    -0.56
     Byrne
    -0.56
    POSITIVE LOGITS
    grand
    1.37
    father
    1.28
    mother
    1.06
    parents
    1.03
    daughter
    1.00
    iosity
    0.96
    uncle
    0.88
    son
    0.87
    sonian
    0.84
    Dad
    0.84
    Activations Density 0.005%

    No Known Activations