INDEX

Explanations

references to reviews or assessments of studies and literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

któ

-0.71

 Schulte

-0.66

 Alba

-0.65

 Dallas

-0.64

 Piet

-0.63

ματο

-0.62

🤣🤣

-0.60

Nat

-0.59

 Dodson

-0.59

 getY

-0.58

POSITIVE LOGITS

 Review

1.60

 review

1.54

 Reviews

1.53

 REVIEW

1.53

 reviews

1.52

review

1.51

Review

1.50

Reviews

1.49

REVIEW

1.47

 reviewer

1.42

Activations Density 0.069%

references to reviews or assessments of studies and literature

No Comments

No Known Activations