INDEX

Explanations

word occurrences related to trends or trending topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 fair

-0.55

 historical

-0.54

 familiare

-0.54

 immédi

-0.53

 barter

-0.53

raire

-0.52

 adil

-0.51

 alternate

-0.51

 gamla

-0.50

alternate

-0.49

POSITIVE LOGITS

 trend

0.97

 '\\;'

0.95

Dot

0.95

 Trend

0.93

 sentiment

0.93

trend

0.90

Dot

0.90

 sensation

0.88

 Sentiment

0.88

OGND

0.85

Activations Density 0.105%

word occurrences related to trends or trending topics

No Comments

No Known Activations