INDEX

Explanations

elements and attributes related to HTML and data representation

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

Characters or symbols followed by letters

np_acts-logits-general · gemini-2.0-flash

Yellow fur

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.94

 itſelf

-1.87

 themſelves

-1.69

ſelf

-1.69

ſelves

-1.68

 doubtnut

-1.67

 Monfieur

-1.60

 ſeveral

-1.58

 Shakspeare

-1.58

Efq

-1.56

POSITIVE LOGITS

1.01

0.96

0.95

0.93

0.91

et

0.89

Activations Density 0.865%

elements and attributes related to HTML and data representation

Characters or symbols followed by letters

Yellow fur

No Comments

No Known Activations