INDEX

Explanations

instances of the word "wonder" 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Palladium

-0.66

 infinitive

-0.66

 itſelf

-0.64

 poffible

-0.61

 degeneracy

-0.61

 Gans

-0.59

 rehearsals

-0.58

 Lettuce

-0.58

 myſelf

-0.58

 latent

-0.58

POSITIVE LOGITS

 gentle

0.67



0.64

gentle

0.61

 devriez

0.60

การ

0.59

се

0.56

ο

0.56

usercontent

0.55

 HttpHeaders

0.55

 pourriez

0.55

Activations Density 0.096%

instances of the word "wonder" in various contexts

No Comments

No Known Activations