INDEX

Explanations

terms related to elections and appointments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 '\\;'

-0.58

ener

-0.56

 zuge

-0.53

向

-0.50

繁

-0.50

выше

-0.49

mybatisplus

-0.48

monde

-0.47

 looked

-0.47

 vốn

-0.47

POSITIVE LOGITS

 elected

1.27

 Elected

1.20

 approved

1.15

elected

1.09

 convicted

1.08

 Approved

1.02

 infected

0.97

 APPROVED

0.95

Approved

0.90

 selected

0.89

Activations Density 0.197%

terms related to elections and appointments

No Comments

No Known Activations