INDEX

Explanations

words related to mutating functions and data manipulation in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

LabelTagHelper

-0.69

 pâtes

-0.59

 setempat

-0.58

 Sociales

-0.58

 alimentazione

-0.58

 palsu

-0.58

 acoper

-0.58

 oignons

-0.57

BeginContext

-0.57

 căr

-0.57

POSITIVE LOGITS

mut

1.48

mut

1.40

Mut

1.18

Mut

1.16

MUT

0.97

MUT

0.96

 mutate

0.81

numerusform

0.80

RunWith

0.71

NameInMap

0.70

Activations Density 0.033%

words related to mutating functions and data manipulation in programming

No Comments

No Known Activations