INDEX

Explanations

numerical data and statistics

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

/**

-0.82

Réalisation

-0.80

 MacGregor

-0.74

 serializers

-0.73

 Maguire

-0.71

 GIPHY

-0.71

 transfieras

-0.70

WriteAttribute

-0.70

 XCTest

-0.70

globalData

-0.70

POSITIVE LOGITS

0.97

0.94

0.92

0.87

Twelve

0.86

twelve

0.85

UNRELATED

0.81

0.80

0.77

0.75

Activations Density 0.155%

numerical data and statistics

No Comments

No Known Activations