INDEX

Explanations

specific programming or code-related keywords and constructs

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

Code, definitions, or version numbers

np_acts-logits-general · gemini-2.0-flash

version number or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

++;

-0.72

-0.71

++;

-0.68

-0.67

"]["

-0.66

']['

-0.64

()==

-0.62

'][

-0.61

 isEqualToString

-0.61

']==

-0.60

POSITIVE LOGITS

 Majefty

1.12

 myſelf

1.09

 pleaſure

1.08

 purpoſe

1.07

 CreateTagHelper

1.03

 houſe

1.03

 preſent

1.02

Efq

1.02

 Anſ

1.00

 Diſ

1.00

Activations Density 0.237%

specific programming or code-related keywords and constructs

Code, definitions, or version numbers

version number or code

No Comments

No Known Activations