© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8117
    Prev
    Next
    INDEX
    Explanations

    phrases related to different aspects of life such as health, community, entertainment, and security

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating concern or discussion about environmental and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.91
    ageddon
    -0.82
    ¬¼
    -0.81
    ģĸ
    -0.78
    ":"/
    -0.74
    Ĥİ
    -0.71
    izen
    -0.71
    ãĥĥãĥĪ
    -0.71
    KEN
    -0.71
    ½
    -0.70
    POSITIVE LOGITS
     including
    1.29
     namely
    1.11
     which
    1.08
     whereas
    1.07
     although
    1.00
     wherein
    1.00
     but
    0.99
     whereby
    0.98
     allowing
    0.97
     includ
    0.96
    Activations Density 0.338%

    No Known Activations