© 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. 16144
    Prev
    Next
    INDEX
    Explanations

    verbs related to making future plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future intentions or plans

    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
    illian
    -0.70
    izabeth
    -0.65
     suscept
    -0.64
    ixel
    -0.64
    aws
    -0.60
    inas
    -0.57
     Heard
    -0.56
    avery
    -0.56
    lang
    -0.55
    wi
    -0.55
    POSITIVE LOGITS
     to
    1.16
     Parenthood
    0.78
     accordingly
    0.75
     onward
    0.72
     onwards
    0.72
    ¶
    0.72
    To
    0.67
    eto
    0.67
     renovations
    0.66
    llor
    0.66
    Activations Density 0.067%

    No Known Activations