© 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. 6-RES-JB
    11. 19780
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "registry"

    oai_token-act-pair · gpt-3.5-turbo

    references to registries, particularly those related to technology and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨ
    -0.87
    ingly
    -0.86
    ing
    -0.84
    ql
    -0.81
    æѦ
    -0.79
    iour
    -0.72
    ions
    -0.71
    IU
    -0.71
    ibly
    -0.67
    iol
    -0.67
    POSITIVE LOGITS
     bom
    0.80
    acht
    0.74
    inding
    0.72
    atory
    0.68
    ukes
    0.68
    agine
    0.65
    uked
    0.64
     Adin
    0.63
    ploy
    0.62
    uzzle
    0.62
    Activations Density 0.118%

    No Known Activations