© 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. 13453
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity, likely related to a brewery named "Black Cloister," its related products, events, and community involvement

    oai_token-act-pair · gpt-3.5-turbo

    references to cloaking or concealment

    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
    raltar
    -0.72
     Murd
    -0.66
    ¤
    -0.66
    Murray
    -0.64
    itar
    -0.64
    anian
    -0.63
    Ļ½
    -0.63
    llah
    -0.63
     Mercury
    -0.63
     WATCHED
    -0.62
    POSITIVE LOGITS
     clo
    1.17
     cloak
    1.04
     Clo
    0.89
     Cloak
    0.87
    SPONSORED
    0.86
     skirts
    0.83
     cloaked
    0.83
    acas
    0.80
     shroud
    0.79
    heses
    0.77
    Activations Density 0.016%

    No Known Activations