Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11058
    Prev
    Next
    INDEX
    Explanations

    words related to the action of choosing or selecting

    oai_token-act-pair · gpt-3.5-turbo

    the term "elect" and its variations in different contexts related to elections and voting processes

    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
    TAG
    -0.74
    beer
    -0.69
     Settlement
    -0.68
    isu
    -0.67
    rama
    -0.66
    tl
    -0.65
     Danger
    -0.64
    War
    -0.61
    raw
    -0.61
     DevOnline
    -0.60
    POSITIVE LOGITS
     elect
    4.32
     Elect
    2.24
    elect
    2.14
     electing
    2.07
     ELECT
    1.81
    Elect
    1.76
     elected
    1.44
     electro
    1.20
     electr
    1.11
     electrom
    1.10
    Activations Density 0.009%

    No Known Activations