Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12367
    Prev
    Next
    INDEX
    Explanations

    phrases expressing introspection and contemplation

    oai_token-act-pair · gpt-3.5-turbo

    references to decision-making processes and discussions about future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accessed
    -0.76
    Introduced
    -0.74
    sbm
    -0.72
    illegal
    -0.72
    bsite
    -0.70
    <?
    -0.70
    \-
    -0.70
    obile
    -0.69
     advertised
    -0.68
    vernight
    -0.67
    POSITIVE LOGITS
     ourselves
    1.46
     anew
    1.15
     oneself
    1.10
     wiser
    1.03
     sanity
    1.01
     yourselves
    1.01
     lessons
    0.96
     humility
    0.89
     truths
    0.88
     hopefully
    0.85
    Activations Density 0.810%

    No Known Activations