INDEX

Explanations

affirmative and assertive expressions, particularly those marked by "actually."

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

zyści

-0.75

ers

-0.73

rmtree

-0.72

erd

-0.69

 Kieran

-0.68

<tr>

-0.67

DMS

-0.67

CIS

-0.66

 Silo

-0.66

 entendido

-0.65

POSITIVE LOGITS

ACTUAL

1.05

 actual

0.93

 actually

0.93

Actually

0.91

actually

0.88

 reales

0.88

 Actually

0.85

 ACTUALLY

0.84

 ACTUAL

0.79

Actual

0.79

Activations Density 0.054%

affirmative and assertive expressions, particularly those marked by "actually."

No Comments

No Known Activations