INDEX

Explanations

terms related to selection and criteria 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etCode

-0.80

karz

-0.79

ocumented

-0.75

ecake

-0.73

EObject

-0.73

 grazia

-0.73

dword

-0.70

باد

-0.69

 nyata

-0.68

 Penh

-0.68

POSITIVE LOGITS

 selection

2.29

 Selection

2.26

 selections

2.13

Selection

2.12

selection

2.08

 Selections

2.05

 selects

1.96

 SELECTION

1.90

 selecting

1.87

 Sele

1.87

Activations Density 0.093%

terms related to selection and criteria in various contexts

No Comments

No Known Activations