INDEX

Explanations

descriptive language that emphasizes skill and mastery in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

djangoproject

-0.70

parsedMessage

-0.58

мую

-0.54

endpush

-0.54

ukunfts

-0.54

 Meier

-0.53

antie

-0.52

tryk

-0.52

addProperty

-0.51

NNN

-0.49

POSITIVE LOGITS

 skill

1.04

 skills

1.00

 habile

0.99

 skillful

0.98

 skillfully

0.95

skill

0.93

 deft

0.92

 expertly

0.89

 proficient

0.89

skills

0.89

Activations Density 0.199%

descriptive language that emphasizes skill and mastery in various contexts

No Comments

No Known Activations