INDEX

Explanations

references to "cover" or "covers" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

BeginContext

-0.57

__":

-0.57

 Dumont

-0.56

bidi

-0.56

iasaan

-0.55

MONS

-0.54

sizeCache

-0.54

}{*}{}

-0.53

httphttps

-0.53

Initializable

-0.53

POSITIVE LOGITS

 cover

4.05

 Cover

3.78

Cover

3.61

cover

3.58

 covers

3.53

 COVER

3.41

 Covers

3.37

Covers

3.14

COVER

3.11

covers

2.92

Activations Density 0.100%

references to "cover" or "covers" in various contexts

No Comments

No Known Activations