INDEX

Explanations

phrases related to critiques and evaluations

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

windowFixed

-0.73

Portale

-0.66

ValueStyle

-0.63

 Emeritus

-0.62

 LoggerFactory

-0.62

AndEndTag

-0.61

Chham

-0.60

escaping

-0.60

contentLoaded

-0.59

 télécharge

-0.59

POSITIVE LOGITS

 attempt

0.86

 attempts

0.79

 attempted

0.75

 failed

0.69

 attempting

0.68

 Attempt

0.67

 tried

0.66

attempts

0.65

 Attempts

0.64

attempt

0.64

Activations Density 0.621%

phrases related to critiques and evaluations

No Comments

No Known Activations