© 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. 1-RES-JB
    11. 3100
    Prev
    Next
    INDEX
    Explanations

    specific locations related to burial or remembrance of the dead

    oai_token-act-pair · gpt-3.5-turbo

    references to cemeteries and graveyards

    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
    axis
    -0.74
    BuyableInstoreAndOnline
    -0.68
    Priv
    -0.67
    bits
    -0.67
    estamp
    -0.67
    Bey
    -0.66
    Const
    -0.65
    Brand
    -0.64
    Paul
    -0.64
    Access
    -0.63
    POSITIVE LOGITS
     Cemetery
    1.21
     cemetery
    1.20
     graveyard
    1.12
    emetery
    1.03
     chapel
    0.96
    conservancy
    0.92
     Graveyard
    0.86
    yard
    0.82
     burying
    0.82
    veyard
    0.80
    Activations Density 0.016%

    No Known Activations