INDEX

Explanations

negative assertions or disagreements regarding established facts and beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Dienst

-0.54

 لينك

-0.53

 nữa

-0.49

ViewImports

-0.49

 abusos

-0.48

odat

-0.47

 Eating

-0.47

 Haven

-0.45

tapkan

-0.45

UNTAIN

-0.44

POSITIVE LOGITS

tdessen

0.86

 Gegenteil

0.77

mergeFrom

0.75

 contrary

0.74

 InputDecoration

0.73

 Instead

0.71

RegressionTest

0.70

脚注の使い方

0.70

 instead

0.67

むしろ

0.67

Activations Density 0.231%

negative assertions or disagreements regarding established facts and beliefs

No Comments

No Known Activations