INDEX

Explanations

programming-related import statements and class declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.58

-0.51

зин

-0.49

-0.47

↵

-0.47

POSITIVE LOGITS

 مرئيه

1.01

ſelf

0.98

 فريبيس

0.98

 myſelf

0.98

NUMX

0.97

DockStyle

0.96

 يتيمه

0.96

 itſelf

0.95

ⓧ

0.94

 Theſe

0.93

Activations Density 0.146%

programming-related import statements and class declarations

No Comments

No Known Activations