INDEX

Explanations

punctuation and formatting related to dialogue or speech

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

ValueStyle

-0.97

verticalLayout

-0.76

msford

-0.76

paravant

-0.69

 الحم

-0.68

impianto

-0.67

gameId

-0.67

 calendriers

-0.66

tsam

-0.66

 Enfield

-0.65

POSITIVE LOGITS

、

1.00

、

0.95

例句

0.92

：

0.88

／

0.87

：（

0.84

）

0.84

、“

0.83

（

0.82

。（

0.82

Activations Density 0.059%

punctuation and formatting related to dialogue or speech

No Comments

No Known Activations