© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17578
    Prev
    Next
    INDEX
    Explanations

    future tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "gonna" reflecting future intentions or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.77
    template
    -0.76
    controlled
    -0.73
    mere
    -0.73
    Reviewed
    -0.72
    rehens
    -0.72
    hips
    -0.72
    san
    -0.66
    Fra
    -0.66
    Express
    -0.66
    POSITIVE LOGITS
     give
    0.93
     be
    0.91
     stick
    0.87
     get
    0.86
     tha
    0.85
     eat
    0.85
     go
    0.84
     wanna
    0.83
     make
    0.83
     nab
    0.81
    Activations Density 0.006%

    No Known Activations