INDEX

Explanations

terms related to candidates and nominations in political contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Fprintf

-0.67

worths

-0.64

ymce

-0.62

cha

-0.61

cales

-0.60

tw

-0.60

GRAFIA

-0.60

Broke

-0.57

ら

-0.56

 StatelessWidget

-0.56

POSITIVE LOGITS

 candidates

1.73

 Candidates

1.70

candidates

1.54

 Candidate

1.54

Candidates

1.53

 CANDIDATE

1.53

 candidate

1.48

Candidate

1.48

CAND

1.37

candidate

1.37

Activations Density 0.119%

terms related to candidates and nominations in political contexts

No Comments

No Known Activations