INDEX

Explanations

probabilities and uncertainties expressed in the text

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

-0.58

-0.57

続く

-0.55

رائ

-0.53

 inginkan

-0.53

on

-0.52

an

-0.51

止ま

-0.51

-0.50

POSITIVE LOGITS

bably

1.25

 probably

1.21

 Probably

1.20

 prolly

1.13

########.

1.13

Probably

1.11

probably

1.06

BufferException

0.98

Gambas

0.96

>*/

0.94

Activations Density 0.089%

probabilities and uncertainties expressed in the text

No Comments

No Known Activations