INDEX

Explanations

strings that indicate metadata or structured data in a code context

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

ChildScrollView

-1.02

 leaſt

-0.94

 initComponents

-0.94

 poffible

-0.93

 myſelf

-0.91

 Partagez

-0.87

 leſs

-0.84

 متعلقه

-0.83

 juſt

-0.83

Geplaatst

-0.83

POSITIVE LOGITS

 string

2.06

 strings

1.96

string

1.85

STRING

1.76

strings

1.75

 String

1.67

 Strings

1.62

 STRING

1.61

String

1.58

Strings

1.51

Activations Density 0.098%

strings that indicate metadata or structured data in a code context

No Comments

No Known Activations