INDEX

Explanations

phrases that indicate taking action or making choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 inac

-0.71

chließend

-0.58

ждую

-0.57

untos

-0.57

://

-0.57

DebuggerNonUser

-0.56

]--;

-0.56

可见

-0.56

WireFormatLite

-0.55

 aprend

-0.54

POSITIVE LOGITS

 CreateTagHelper

0.71

 Sélectionnez

0.71

 opting

0.68

 opted

0.66

ValueStyle

0.65

 оригіналу

0.64

opt

0.63

 consultato

0.62

Opt

0.61

 opts

0.60

Activations Density 0.113%

phrases that indicate taking action or making choices

No Comments

No Known Activations