INDEX

Explanations

instances of verbs and auxiliary verbs indicating action or intention

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

InlineData

-0.72

 ſtate

-0.72

 poffible

-0.71

ſy

-0.71

 purpoſe

-0.69

 myſelf

-0.69

 ſtand

-0.68

 /\.(

-0.68

 fevere

-0.67

 houſe

-0.66

POSITIVE LOGITS

 seem

0.89

 seems

0.84

 seemed

0.80

riwal

0.78

 scheint

0.73

seems

0.71

 semblent

0.70

 Parece

0.67

 snippetHide

0.66

Seems

0.65

Activations Density 0.061%

instances of verbs and auxiliary verbs indicating action or intention

No Comments

No Known Activations