© 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. 4-RES-JB
    11. 4176
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future intentions or plans

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "gonna," indicating future intentions or actions

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

    No Comments

    Negative Logits
    controlled
    -0.77
    rehens
    -0.75
    template
    -0.75
    lain
    -0.73
    mere
    -0.73
    contained
    -0.69
    croft
    -0.69
    amped
    -0.69
    lying
    -0.69
    Protect
    -0.68
    POSITIVE LOGITS
     give
    0.96
     be
    0.95
     get
    0.92
     stick
    0.88
     make
    0.88
     go
    0.88
     tha
    0.87
     buckle
    0.85
     weigh
    0.84
     bring
    0.84
    Activations Density 0.010%

    No Known Activations