INDEX

Explanations

phrases related to the analysis of language and communication

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

Follows personal titles (Mr, Mrs, Dr)

np_acts-logits-general · gemini-2.0-flash

people's titles

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

 Juda

-0.69

SOP

-0.68

#+#

-0.66

+:+

-0.64

addContainerGap

-0.64

mybatisplus

-0.62

 Assy

-0.60

 nakalista

-0.59

 WeChat

-0.59

ANTLR

-0.59

POSITIVE LOGITS

Mr

0.91

Mrs

0.75

Mr

0.75

Dr

0.75

자인

0.69

这位

0.67

"]);

0.67

Dr

0.66

Mrs

0.63

 Professor

0.61

Activations Density 4.320%

phrases related to the analysis of language and communication

Follows personal titles (Mr, Mrs, Dr)

people's titles

No Comments

No Known Activations