INDEX

Explanations

phrases related to treatment and fairness towards individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hecht

-0.59

helle

-0.51

 Giordano

-0.50

 bénéficiaire

-0.50

 Ubic

-0.49

 interlocking

-0.49

oxu

-0.49

XSSF

-0.48

ricist

-0.47

tadiene

-0.47

POSITIVE LOGITS

 treat

1.13

 treated

1.11

 treating

1.08

treated

1.04

 Treat

1.03

Treat

0.98

 TREAT

0.97

treat

0.96

 Treated

0.96

 treats

0.95

Activations Density 0.173%

phrases related to treatment and fairness towards individuals or groups

No Comments

No Known Activations