INDEX

Explanations

the word 'to' and its variations in 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 habet

-0.78

 mourut

-0.78

 poffible

-0.76

 realisation

-0.75

 Jefus

-0.74

Personensuche

-0.73

 venait

-0.72

 occaf

-0.72

 mobilisation

-0.71

 greateſt

-0.69

POSITIVE LOGITS

be

1.10

put

0.93

 take

0.89

 make

0.83

do

0.81

 become

0.81

 give

0.79

 have

0.79

run

0.78

 grow

0.76

Activations Density 0.756%

the word 'to' and its variations in different contexts

No Comments

No Known Activations