INDEX

Explanations

technical terms and concepts related to procedures, systems, and tools in a healthcare or educational context

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

followed by "that" or similar relative pronouns

np_acts-logits-general · gemini-2.0-flash

that/which clauses

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

IVEREF

-0.66

::*;

-0.63

hoeddwyd

-0.61

bootstrapcdn

-0.60

CppCodeGen

-0.60

awtextra

-0.60

ArrowToggle

-0.59

θεν

-0.57

 <=",

-0.54

rxjs

-0.53

POSITIVE LOGITS

 that

3.02

that

1.85

 which

1.83

who

1.68

 که

1.61

 που

1.55

 whose

1.52

ที่

1.41

 которые

1.31

 которая

1.31

Activations Density 3.200%

technical terms and concepts related to procedures, systems, and tools in a healthcare or educational context

followed by "that" or similar relative pronouns

that/which clauses

No Comments

No Known Activations