INDEX

Explanations

markers that indicate the beginning or end of a document

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

fjspx

-1.20

 ―――――

-1.20

 iſt

-1.19

脚注の使い方

-1.14

ſelves

-1.13

 myſelf

-1.12

 initComponents

-1.10

LookAnd

-1.09

IndentedString

-1.09

 pleaſure

-1.07

POSITIVE LOGITS

↵

0.80

0.73

0.67

0.63

0.62

↵↵

0.61

0.60

0.58

but

0.57

</strong>

0.56

Activations Density 0.288%

markers that indicate the beginning or end of a document

No Comments

No Known Activations