INDEX

Explanations

references to ArrayList data structures in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Te

-0.68

-0.67

pe

-0.65

لمين

-0.65

Sel

-0.65

さ

-0.62

Sel

-0.59

+#+#

-0.59

POSITIVE LOGITS

ArrayList

1.79

 ArrayList

1.73

 myſelf

1.03

antaranya

1.01

 themſelves

0.98

 purpoſe

0.95

 dieß

0.94

 ―――――

0.94

 iſt

0.93

 ſche

0.92

Activations Density 0.039%

references to ArrayList data structures in code

No Comments

No Known Activations