INDEX

Explanations

references to blogs

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

 purpoſe

-0.92

 igång

-0.87

igreja

-0.86

IBLIO

-0.86

Efq

-0.85

ghijklmnop

-0.84

 myſelf

-0.83

NUMX

-0.82

Imágenes

-0.82

 themſelves

-0.81

POSITIVE LOGITS

0.65

is

0.55

es

0.54

 tops

0.51

кра

0.50

Us

0.50

Body

0.50

Fit

0.50

 including

0.49

des

0.49

Activations Density 0.400%

references to blogs

No Comments

No Known Activations