INDEX

Explanations

terms related to non-compliance and specific medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 neuve

-0.75

 ſche

-0.74

 ainfi

-0.72

 Beſ

-0.68

 purpoſe

-0.67

lámpara

-0.67

 Monfieur

-0.67

 malheureux

-0.66

 Theſe

-0.66

 efficaces

-0.66

POSITIVE LOGITS

Non

0.91

non

0.87

NON

0.84

Non

0.81

 nong

0.75

 nons

0.73

 Nons

0.71

non

0.70

NON

0.67

非

0.62

Activations Density 0.160%

terms related to non-compliance and specific medical conditions

No Comments

No Known Activations