INDEX

Explanations

common phrases that indicate frequency or typicality in actions or characteristics

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

 الاطلاع

-0.66

 étoient

-0.62

 Houſe

-0.62

setViewName

-0.58

 ſever

-0.57

 houſe

-0.57

 Majefty

-0.57

 poffe

-0.57

 ſtate

-0.57

PhysRevD

-0.57

POSITIVE LOGITS

 also

0.67

 either

0.64

 even

0.61

SuccessListener

0.54

 perhaps

0.54

 aapt

0.54

 Projektu

0.53

either

0.53

 include

0.52

 kèm

0.52

Activations Density 0.392%

common phrases that indicate frequency or typicality in actions or characteristics

No Comments

No Known Activations