INDEX

Explanations

content related to formal responsibilities and decision-making in various contexts

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

تقاوى

-0.78

bbene

-0.60

 resourceCulture

-0.60

 >=",

-0.60

 Normdatei

-0.59

 téléph

-0.58

 typelib

-0.56

Jeografia

-0.54

 gradova

-0.54

GraphicsUnit

-0.53

POSITIVE LOGITS

 instead

3.09

 Instead

2.93

Instead

2.88

instead

2.65

 vielmehr

2.08

tdessen

2.06

 invece

1.98

 istället

1.90

 вместо

1.81

 justru

1.77

Activations Density 0.804%

content related to formal responsibilities and decision-making in various contexts

No Comments

No Known Activations