INDEX

Explanations

references to "feed" in various contexts, especially related to data streams or input sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Xperia

-0.81

*/].

-0.80

propTypes

-0.79

erton

-0.77

psons

-0.76

userRepository

-0.72

Ahn

-0.72

clonal

-0.70

TResult

-0.70

Precalculus

-0.70

POSITIVE LOGITS

 feed

2.46

 feeds

2.37

feed

2.32

 Feed

2.31

Feed

2.25

feeds

2.02

 FEED

2.02

 Feeds

1.98

FEED

1.90

Feeds

1.83

Activations Density 0.034%

references to "feed" in various contexts, especially related to data streams or input sources

No Comments

No Known Activations