INDEX

Explanations

references to time, values, and data manipulation in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Rüyada

-0.62

Twice

-0.56

queryInterface

-0.56

TagHelper

-0.54

 <<<<<<<<<<<<<<

-0.54

twice

-0.52

 endregion

-0.52

shank

-0.51

 Twice

-0.51

ioen

-0.51

POSITIVE LOGITS

 thousand

0.91

thousand

0.85

Thousand

0.84

 Thousand

0.83

 THOUS

0.74

 hundred

0.70

 thousands

0.69

Million

0.63

million

0.63

Mille

0.61

Activations Density 0.435%

references to time, values, and data manipulation in programming or technical contexts

No Comments

No Known Activations