INDEX

Explanations

terms related to depth measurements or profiles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Caw

-0.69

walde

-0.62

bigg

-0.61

 Mill

-0.59

^^^^^^^^

-0.59

RegistryLite

-0.58

Mad

-0.57

mill

-0.57

AccessorTable

-0.56

 Silverman

-0.56

POSITIVE LOGITS

 depth

2.57

 Depth

2.42

 DEPTH

2.39

Depth

2.29

depth

2.27

DEPTH

2.03

 depths

2.00

 profundidad

1.55

 profondeur

1.47

 profondità

1.33

Activations Density 0.141%

terms related to depth measurements or profiles

No Comments

No Known Activations

terms related to depth measurements or profiles

No Comments

No Known Activations