INDEX

Explanations

phrases that highlight product features and qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

encodeWith

-0.72

LLocation

-0.65

ospels

-0.64

 getItemId

-0.58

Personensuche

-0.58

providedIn

-0.57

 للمعارف

-0.57

\{\\

-0.56

 विश्वसनीयता

-0.55

AddTagHelper

-0.54

POSITIVE LOGITS

 aesthetic

0.69

 aesthetics

0.67

 elegance

0.61

 artistic

0.56

 AttributeSet

0.54

 Aesthetic

0.54

 ornament

0.53

 decoration

0.52

 style

0.51

 accent

0.50

Activations Density 0.144%

phrases that highlight product features and qualities

No Comments

No Known Activations