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. 11-RES-JB
    6. 20613
    Prev
    Next
    INDEX
    Explanations

    phrases related to the laws of physics and physical phenomena

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the laws of physics and their implications

    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
     Staten
    -0.63
    everal
    -0.62
     Dunk
    -0.60
    ursday
    -0.58
     millennials
    -0.55
     resur
    -0.55
    nesday
    -0.55
     thous
    -0.55
     veteran
    -0.54
     Cologne
    -0.54
    POSITIVE LOGITS
     insofar
    1.20
     unless
    1.08
    .[
    1.07
     (=
    1.00
     irrespective
    0.99
    .(
    0.98
     ([
    0.98
    unless
    0.94
    .
    0.93
    ;
    0.93
    Activations Density 0.453%

    No Known Activations