INDEX

Explanations

expressions describing the quality and nature of experiences or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

❋

-0.75

 CanadaChoose

-0.69

Sklici

-0.68

 publiques

-0.67

Diwedd

-0.67

 Sarko

-0.67

 nationaux

-0.67

LookAnd

-0.65

 artificiales

-0.63

 trefoil

-0.63

POSITIVE LOGITS

the

0.58

ური

0.56

uelas

0.55

WebVitals

0.54

 difficult

0.52

all

0.52

lippery

0.52

UVWXYZ

0.51

 little

0.51

Activations Density 0.080%

expressions describing the quality and nature of experiences or items

No Comments

No Known Activations