INDEX

Explanations

phrases and terms relating to specific topics or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 kasarigan

-0.71

 незавершена

-0.66

 ""],

-0.65

<_>

-0.60

__":

-0.60

'])->

-0.60

KURZBESCHREIBUNG

-0.59

Referencies

-0.59

 AssemblyCulture

-0.57

+#+#

-0.57

POSITIVE LOGITS

 such

3.56

such

2.97

 like

2.71

 SUCH

2.42

Such

2.37

 Such

2.29

 telles

2.19

 takich

2.18

 seperti

2.11

 såsom

2.10

Activations Density 2.549%

phrases and terms relating to specific topics or categories

No Comments

No Known Activations