INDEX

Explanations

terms related to health and 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 @ 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

oa̍t

-0.79

"):

-0.67

quelize

-0.63

 FetchType

-0.62

 invokingState

-0.60

 tartalomajánló

-0.59

 NUKAT

-0.59

 سكانية

-0.58

fice

-0.57

RTGC

-0.57

POSITIVE LOGITS

hu

0.82

GroupLayout

0.79

hu

0.78

eu

0.67

HU

0.65

forChild

0.62

EndContext

0.58

zz

0.58

ORD

0.57

Hu

0.57

Activations Density 1.692%

terms related to health and medical conditions

No Comments

No Known Activations