INDEX

Explanations

phrases indicating necessity or obligation

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

tvguidetime

-0.68

RegistryLite

-0.65

<bos>

-0.59

windowFixed

-0.58

 Peres

-0.58

rungsseite

-0.57

PRWEB

-0.57

 gevolg

-0.57

 referenties

-0.56

 ویکی

-0.56

POSITIVE LOGITS

 need

0.89

 needs

0.85

NEED

0.80

 should

0.73

 gotta

0.72

 besoins

0.72

 Deber

0.71

 Debe

0.71

Neces

0.70

 harus

0.70

Activations Density 0.081%

phrases indicating necessity or obligation

No Comments

No Known Activations