INDEX

Explanations

references to "host" in various contexts, particularly in computing or network configurations

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

onedDateTime

-0.49

bl

-0.47

Ma

-0.47

 Mund

-0.47

cipar

-0.47

Pa

-0.45

cessive

-0.45

The

-0.44

Sen

-0.44

POSITIVE LOGITS

 grapes

1.23

 grape

1.22

grape

1.12

Berry

1.05

berry

1.03

 berry

1.01

Grape

1.00

 Berry

0.99

 Grapes

0.98

 Grape

0.91

Activations Density 0.076%

references to "host" in various contexts, particularly in computing or network configurations

No Comments

No Known Activations