INDEX

Explanations

mentions of the term "duration."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.00

 Diſ

-1.00

 Anſ

-0.99

 leaſt

-0.97

 Theſe

-0.96

 faſt

-0.90

 purpoſe

-0.89

 Houſe

-0.87

 ―――――

-0.85

 miſ

-0.85

POSITIVE LOGITS

 duration

0.76

est

0.65

0.64

0.62

duration

0.62

 correlation

0.61

0.59

Est

0.58

 program

0.55

EST

0.52

Activations Density 0.220%

mentions of the term "duration."

No Comments

No Known Activations