INDEX

Explanations

references to specific episodes in a series or program

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 للمعارف

-0.75

thenia

-0.69

er

-0.65

erati

-0.63

farin

-0.62

WIR

-0.60

REE

-0.59

 DriverManager

-0.59

asl

-0.59

Hvem

-0.58

POSITIVE LOGITS

 episode

2.17

episode

2.05

 episodes

2.05

 Episode

1.96

 Episodes

1.89

Episode

1.80

episodes

1.69

 EPISODE

1.67

Episodes

1.61

pisode

1.57

Activations Density 0.079%

references to specific episodes in a series or program

No Comments

No Known Activations

references to specific episodes in a series or program

No Comments

No Known Activations