INDEX

Explanations

phrases indicating the need for further research and studies across 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ModelBuilder

-0.53

TagHelper

-0.49

 مُعرِّف

-0.48

êcher

-0.46

ोंने

-0.45

MigrationBuilder

-0.45

pyx

-0.45

 صوتيه

-0.43

 linkovi

-0.43

lusst

-0.43

POSITIVE LOGITS

 needed

3.28

 required

3.19

 necessary

3.15

needed

2.85

required

2.82

 Needed

2.77

necessary

2.73

 Required

2.69

Required

2.55

 Necessary

2.54

Activations Density 0.977%

phrases indicating the need for further research and studies across various contexts

No Comments

No Known Activations