INDEX

Explanations

prompts for user input

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

bihan

-0.72

akuan

-0.71

addObject

-0.71

 Whigs

-0.71

schmidt

-0.70

emf

-0.70

oshiba

-0.69

 Lawson

-0.69

 imageName

-0.68

Morrison

-0.68

POSITIVE LOGITS

Enter

1.89

 Enter

1.76

 ENTER

1.74

 enter

1.73

enter

1.61

 entered

1.59

ENTER

1.58

 enters

1.54

 Entering

1.44

 entering

1.43

Activations Density 0.041%

prompts for user input

No Comments

No Known Activations