INDEX

Explanations

references to institutions and their varying forms and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

DockStyle

-0.85

 extradition

-0.78

 numé

-0.76

 cristiana

-0.74

 Sartre

-0.74

 Sheryl

-0.74

 Waray

-0.74

 médicaux

-0.73

 rosary

-0.73

 Ayur

-0.73

POSITIVE LOGITS

 institution

2.11

 institutions

2.07

 Institution

1.89

 Institutions

1.86

institution

1.81

Institution

1.66

institutions

1.64

 institutional

1.59

 INSTITUTION

1.55

Institutional

1.51

Activations Density 0.047%

references to institutions and their varying forms and associations

No Comments

No Known Activations