INDEX

Explanations

technical terms and function declarations associated with programming and coding structures

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

after "language" or related to language translation

np_acts-logits-general · gemini-2.0-flash

language translation and processing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

conversion

-0.96

 creation

-0.92

 conversion

-0.91

creation

-0.91

expansion

-0.86

 restoration

-0.85

transformation

-0.84

removal

-0.83

 transformation

-0.83

 expansion

-0.82

POSITIVE LOGITS

 calibrate

0.91

 certify

0.89

 distribute

0.88

 authorize

0.86

 optimize

0.86

 simulate

0.84

 regulate

0.84

 cultivate

0.83

 analyze

0.83

 evaluate

0.83

Activations Density 0.365%

technical terms and function declarations associated with programming and coding structures

after "language" or related to language translation

language translation and processing

No Comments

No Known Activations