© 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. 11-RES-JB
    11. 18487
    Prev
    Next
    INDEX
    Explanations

    phrases related to time passing and changing situations

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to change and adaptation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UNCLASSIFIED
    -0.72
    ipal
    -0.68
    ãĥ©ãĥ³
    -0.59
     Kissinger
    -0.57
     McAuliffe
    -0.57
    pdf
    -0.56
     unspecified
    -0.56
    iliary
    -0.56
     withdraw
    -0.55
     withdrew
    -0.53
    POSITIVE LOGITS
    Thankfully
    0.99
    Luckily
    0.98
    Fortunately
    0.89
    Recently
    0.87
     however
    0.86
     lately
    0.82
     thankfully
    0.79
     luckily
    0.78
     Thankfully
    0.78
    sometimes
    0.77
    Activations Density 0.722%

    No Known Activations