INDEX

Explanations

references to specific names, particularly "man" related terms and their variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nahilalakip

-0.87

']")

-0.87

ruptcy

-0.85

 glut

-0.84

piac

-0.84

 '\\;'

-0.81

hetics

-0.81

 Holbrook

-0.80

 للمعارف

-0.80

 betweenstory

-0.80

POSITIVE LOGITS

Man

1.67

man

1.59

Man

1.59

MAN

1.56

man

1.51

MAN

1.35

 mans

1.22

 woman

1.17

 Woman

1.14

Mans

1.10

Activations Density 0.085%

references to specific names, particularly "man" related terms and their variations

No Comments

No Known Activations