INDEX

Explanations

continuous use of the verbs 'have' and 'has'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 térm

-0.71

 feroit

-0.69

 engraçadas

-0.65

 Jefus

-0.62

 inalámb

-0.60

 recupero

-0.60

 contratación

-0.60

 auroit

-0.60

scribe

-0.59

 urbanas

-0.59

POSITIVE LOGITS

 indeed

0.85

 actually

0.81

 also

0.81

 CreateTagHelper

0.75

 been

0.74

 autorytatywna

0.74

 certainly

0.73

 always

0.70

not

0.70

put

0.68

Activations Density 0.289%

continuous use of the verbs 'have' and 'has'

No Comments

No Known Activations