INDEX

Explanations

sequences of numerical values and specific formatting symbols

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

RegressionTest

-1.03

Vos

-0.92

nodoc

-0.91

 Paxton

-0.91

 Fargo

-0.91

WriteLiteral

-0.90

*~*~

-0.90

 CreateTagHelper

-0.88

complexType

-0.87

pasta

-0.84

POSITIVE LOGITS

1.14

1.13

1.12

1.03

1.01

0.87

0.84

iarkan

0.83

</i>

0.80

 Prussian

0.78

Activations Density 0.082%

sequences of numerical values and specific formatting symbols

No Comments

No Known Activations