INDEX

Explanations

the word "ever" and its variations across different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 跳转至

-0.77

ToBounds

-0.68

بان

-0.63

pacho

-0.63

 Laine

-0.62

 Williams

-0.61

schild

-0.60

 Hatfield

-0.60

 ronde

-0.60

scriptcase

-0.60

POSITIVE LOGITS

 ever

3.20

 Ever

2.79

 EVER

2.79

ever

2.72

Ever

2.69

EVER

2.38

 jemals

1.55

 Everett

1.45

 ooit

1.40

 Evergreen

1.30

Activations Density 0.044%

the word "ever" and its variations across different contexts

No Comments

No Known Activations