INDEX

Explanations

specific phrases or constructs related to conditional or regulatory language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 myſelf

-1.15

 pleaſure

-0.97

ſelf

-0.96

 whoſe

-0.94

 Houſe

-0.93

 Majefty

-0.93

 Theſe

-0.92

 ―――――

-0.92

 itſelf

-0.91

 Monfieur

-0.91

POSITIVE LOGITS

<bos>

2.45

1.20

1.10

’

1.07

0.98

0.92

↵

0.90

",

0.89

',

0.87

”

0.87

Activations Density 2.648%

specific phrases or constructs related to conditional or regulatory language

No Comments

No Known Activations