INDEX

Explanations

terms indicating significance or substantial impact

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 encarga

-0.60

vnd

-0.56

AspNetCore

-0.55

 interchangeably

-0.54

RunWith

-0.52

İstinadlar

-0.51

Referanser

-0.51

 henvisninger

-0.51

 CYTHON

-0.49

설

-0.49

POSITIVE LOGITS

 significant

1.46

 substantial

1.45

 Substantial

1.40

 Significant

1.36

 substantially

1.36

Significant

1.35

 considerable

1.32

substantial

1.30

 signifikan

1.29

 appreciable

1.29

Activations Density 0.308%

terms indicating significance or substantial impact

No Comments

No Known Activations