INDEX

Explanations

words related to medical conditions and health impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

verläs

-0.95

jestic

-0.94

dellin

-0.92

ledad

-0.91

xffff

-0.91

paravant

-0.87

Viitteet

-0.86

ConstraintMaker

-0.86

 Sanz

-0.85

glise

-0.84

POSITIVE LOGITS

er

1.18

ed

1.04

ing

0.91

ater

0.88

eder

0.85

nder

0.84

ized

0.83

ber

0.82

ه

0.78

BER

0.77

Activations Density 0.109%

words related to medical conditions and health impacts

No Comments

No Known Activations