© 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. 11-RES-JB
    11. 352
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or requirements that need to be met in order to achieve a certain outcome

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements implying necessity or requirement

    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
     Rite
    -0.64
     Correct
    -0.62
     Cumber
    -0.61
     calmed
    -0.61
    Fill
    -0.61
    ilar
    -0.60
     debunked
    -0.59
    enhagen
    -0.59
    answered
    -0.59
    chy
    -0.57
    POSITIVE LOGITS
     intend
    1.09
     aspire
    1.05
     want
    1.05
     intends
    1.00
     hopes
    1.00
     hope
    1.00
     wants
    0.96
     plan
    0.90
    ever
    0.90
     aim
    0.89
    Activations Density 0.153%

    No Known Activations