INDEX

Explanations

dialogue and related actions between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ChildScrollView

-0.71

rungsseite

-0.54

antaranya

-0.49

}{*}{

-0.49

grà

-0.48

zzá

-0.47

Portail

-0.47

Koordinaten

-0.47

VIAF

-0.46

SBATCH

-0.46

POSITIVE LOGITS

脚注の使い方

0.77

DebuggerStep

0.77

TagMode

0.66

HideFlags

0.58

kezett

0.57

nodoc

0.57

oredCriteria

0.56

 nahilalakip

0.53

;->

0.53

statusText

0.53

Activations Density 0.041%

dialogue and related actions between characters

No Comments

No Known Activations