INDEX

Explanations

structured data or code blocks in programming-related documents

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

Code snippets or incomplete code

np_acts-logits-general · gemini-2.0-flash

code syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Infórmanos

-0.87

SharedDtor

-0.85

 vooz

-0.79

pecabe

-0.75

exitRule

-0.74

 ContentValues

-0.73

ientras

-0.71

parsedMessage

-0.70

 queſta

-0.70

%)$

-0.70

POSITIVE LOGITS

1.13

1.12

1.11

0.98

0.96

0.95

0.94

0.93

0.91

Activations Density 0.058%

structured data or code blocks in programming-related documents

Code snippets or incomplete code

code syntax and structure

No Comments

No Known Activations