INDEX

Explanations

repeated instances of periods, indicating sentence endings in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ſelf

-0.92

 Houſe

-0.91

 مشين

-0.90

RegressionTest

-0.88

 Anſ

-0.87

 ſind

-0.85

 juſ

-0.84

 Monfieur

-0.84

 ſche

-0.84

 itſelf

-0.83

POSITIVE LOGITS

0.80

0.65

0.62

0.61

0.56

and

0.55

0.53

an

0.52

://

0.52

0.51

Activations Density 0.072%

repeated instances of periods, indicating sentence endings in the text

No Comments

No Known Activations