INDEX

Explanations

updates and improvements related to software versions and releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 CreateTagHelper

-0.90

 utafitiHapana

-0.82

GEBURTSDATUM

-0.81

mybatisplus

-0.81

########.

-0.73

#+#

-0.72

 betweenstory

-0.72

rawDesc

-0.71

 ProtoMessage

-0.71

 jsPsych

-0.70

POSITIVE LOGITS

is

1.09

 also

1.08

 always

1.02

 still

1.01

has

0.99

 already

0.99

 just

0.97

 usually

0.96

 often

0.94

 actually

0.93

Activations Density 0.025%

updates and improvements related to software versions and releases

No Comments

No Known Activations