© 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. 1-RES-JB
    11. 3965
    Prev
    Next
    INDEX
    Explanations

    words related to the functionality or operation of systems or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various functions or roles in systems and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âķIJâķIJ
    -0.79
     Conquest
    -0.71
    ×Ķ
    -0.70
    Hat
    -0.70
    ש
    -0.69
    ×ŀ
    -0.67
    ת
    -0.66
     Hemp
    -0.65
    ×
    -0.65
     Patriarch
    -0.64
    POSITIVE LOGITS
     functions
    1.15
     Functions
    0.88
    igmatic
    0.85
    hops
    0.84
    afety
    0.84
    function
    0.80
     function
    0.79
    matic
    0.79
    adian
    0.79
    afe
    0.79
    Activations Density 0.010%

    No Known Activations