© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2433
    Prev
    Next
    INDEX
    Explanations

    things that are given or provide something to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    the word "gives" and its associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    к
    -0.63
     widespread
    -0.59
     decades
    -0.54
    urg
    -0.54
     ongoing
    -0.53
     retard
    -0.53
     federal
    -0.53
     Horizons
    -0.52
     domestic
    -0.52
     large
    -0.51
    POSITIVE LOGITS
     gives
    2.94
     provides
    2.06
     allows
    2.03
     lends
    1.94
     gave
    1.93
     helps
    1.83
     lets
    1.81
     assures
    1.80
     introduces
    1.78
     enables
    1.78
    Activations Density 0.010%

    No Known Activations