INDEX

Explanations

references to entries in a structured data format, such as lists or arrays

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

 kwargs

-0.87

펙

-0.80

MemoryWarning

-0.78

 nahilalakip

-0.77

 otomatig

-0.75

couvrez

-0.75

 viewModel

-0.73

djangoproject

-0.73

 }}$}

-0.73

displayquote

-0.73

POSITIVE LOGITS

 entry

2.39

 Entry

2.26

entry

2.17

Entry

2.13

 entries

2.07

 ENTRY

2.05

 Entries

1.93

ENTRY

1.93

Entries

1.91

entries

1.86

Activations Density 0.057%

references to entries in a structured data format, such as lists or arrays

No Comments

No Known Activations