© 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. 18503
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific fictional character named "Sn"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Sn" followed by a number, indicating the presence of specific entities or items related to a series

    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
     secrecy
    -0.79
    xual
    -0.79
     Sunni
    -0.70
     [|
    -0.67
     patriarchy
    -0.65
     Hezbollah
    -0.64
     narciss
    -0.63
     limited
    -0.63
     pacif
    -0.61
    upon
    -0.61
    POSITIVE LOGITS
    ook
    1.16
    icket
    1.12
    appy
    1.10
    akes
    1.09
    ugg
    1.09
    agging
    1.09
    igger
    1.08
    oot
    1.06
    apping
    1.04
    ipers
    1.03
    Activations Density 0.013%

    No Known Activations