INDEX

Explanations

phrases indicating alternatives or contrasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

saraba

-0.77

quelize

-0.68

 AssemblyVersion

-0.66

تقاوى

-0.63

 NgModule

-0.62

 fieldNum

-0.62

jspb

-0.61

sizeCache

-0.60

AccessFile

-0.58

QtWidgets

-0.58

POSITIVE LOGITS

 Instead

0.94

Instead

0.93

tdessen

0.88

 instead

0.88

uttosto

0.76

instead

0.75

而是

0.72

 Rather

0.72

 बजाय

0.71

 istället

0.69

Activations Density 0.283%

phrases indicating alternatives or contrasts

No Comments

No Known Activations