INDEX

Explanations

references to factors, evidence, and relationships 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 @ 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

はじめに

-0.84

tanleria

-0.78

 CreateTagHelper

-0.72

 définiti

-0.63

 fiecare

-0.60

addGap

-0.59

PAIGN

-0.59

 rinnov

-0.59

 gyhoeddwyd

-0.58

 auroit

-0.57

POSITIVE LOGITS

other

0.77

Other

0.76

 other

0.74

 Other

0.72

的其他

0.68

 OTHER

0.67

Others

0.66

 outros

0.66

 其他

0.65

其他

0.64

Activations Density 0.520%

references to factors, evidence, and relationships in various contexts

No Comments

No Known Activations