© 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. 0-RES-JB
    11. 11996
    Prev
    Next
    INDEX
    Explanations

    phrases related to motives or reasons behind actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "motive" and its variations, indicating discussions around intentions or reasons behind actions

    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
    Zone
    -0.75
     dot
    -0.66
     Unch
    -0.63
    guard
    -0.63
     Certified
    -0.62
     Turtle
    -0.61
    WR
    -0.61
     Wide
    -0.59
    Wide
    -0.59
    hops
    -0.58
    POSITIVE LOGITS
     motive
    3.51
     motives
    3.30
     motivations
    2.48
     motivation
    1.86
    otive
    1.32
     rationale
    1.29
     motiv
    1.25
     impulse
    1.22
     intentions
    1.15
     pretext
    1.13
    Activations Density 0.019%

    No Known Activations