INDEX

Explanations

references to various programming or testing functions and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Neighbor

-0.63

alquiler

-0.60

neighborhood

-0.56

lização

-0.54

 publiques

-0.53

 vectorielles

-0.53

stretchr

-0.53

 neighbourhood

-0.51

 dépla

-0.51

Neighbor

-0.51

POSITIVE LOGITS

iled

0.81

 '\\;'

0.79

ills

0.72

ily

0.70

ILED

0.69

]]

0.68

illed

0.67

ils

0.67

Tur

0.63

iling

0.60

Activations Density 2.001%

references to various programming or testing functions and terms

No Comments

No Known Activations