INDEX

Explanations

instances of the word "begin" in various forms, especially when used in the context of starting new actions or processes

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

 مرئيه

-0.85

ضان

-0.83

-0.78

StructEnd

-0.76

 Cowper

-0.75

λέον

-0.74

UVWXYZ

-0.73

UTERS

-0.72

galus

-0.71

 Lewis

-0.70

POSITIVE LOGITS

 beginning

1.61

 Beginning

1.59

 BEGINNING

1.53

beginning

1.52

Beginning

1.51

 Begin

1.48

 begin

1.44

 Beginnings

1.42

 beginnings

1.39

Begin

1.34

Activations Density 0.058%

instances of the word "begin" in various forms, especially when used in the context of starting new actions or processes

No Comments

No Known Activations