INDEX

Explanations

phrases that indicate assumptions or uncertainty regarding a diagnosis or situation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

WebElementEntity

-0.58

tron

-0.58

 Gorb

-0.57

 drow

-0.53

TRON

-0.53

 ſeveral

-0.51

 Shakspeare

-0.51

nastics

-0.51

 itſelf

-0.50

 distributive

-0.50

POSITIVE LOGITS

Geplaatst

0.79

 CreateTagHelper

0.75

 autorytatywna

0.73

 مشين

0.73

msgTypes

0.65

Билгалдахарш

0.62

Erreferentziak

0.60

 transfieras

0.59

Искәрмәләр

0.59

SharedCtor

0.58

Activations Density 0.421%

phrases that indicate assumptions or uncertainty regarding a diagnosis or situation

No Comments

No Known Activations