© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 9929
    Prev
    Next
    INDEX
    Explanations

    expressions related to abstract concepts or considerations

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "matter" or issues of significance and importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARP
    -0.87
    ãĥ³ãĤ¸
    -0.87
    ©¶æ
    -0.79
    NetMessage
    -0.78
    ãĥīãĥ©ãĤ´ãĥ³
    -0.77
    elta
    -0.72
    OWN
    -0.71
    asio
    -0.68
    ãĥ¼ãĥĨ
    -0.68
    ingo
    -0.67
    POSITIVE LOGITS
    ional
    1.06
    enance
    0.85
     pertaining
    0.78
    icular
    0.78
     surrounding
    0.77
    forward
    0.75
    ials
    0.74
    awei
    0.73
     matters
    0.73
     relating
    0.72
    Activations Density 0.039%

    No Known Activations