INDEX

Explanations

declarations and definitions in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 myſelf

-0.83

 itſelf

-0.82

 reaſon

-0.79

脚注の使い方

-0.78

 themſelves

-0.78

 Reſ

-0.76

 auffi

-0.75

 ſch

-0.75

 ―――――

-0.74

 Anſ

-0.74

POSITIVE LOGITS

var

0.82

">//

0.70

 func

0.70

var

0.57

::*;

0.57

Cer

0.51

ReusableCell

0.51

:✨

0.49

Cer

0.48

isEqualTo

0.47

Activations Density 0.180%

declarations and definitions in programming code

No Comments

No Known Activations