© 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. 10-RES-JB
    11. 13766
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    oai_token-act-pair · gpt-3.5-turbo

    actions or instructions, particularly those that suggest methods or solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.67
     Respons
    -0.65
    FX
    -0.64
    comings
    -0.62
    mails
    -0.62
     Ninth
    -0.61
    soever
    -0.61
    accompan
    -0.61
    DAQ
    -0.61
     Worth
    -0.60
    POSITIVE LOGITS
     minimize
    1.22
     maximize
    1.20
     eliminate
    1.17
     educate
    1.16
     create
    1.13
     ensure
    1.12
     empower
    1.12
     isolate
    1.12
     convince
    1.12
     deprive
    1.11
    Activations Density 0.149%

    No Known Activations