INDEX

Explanations

questions and inquiries about actions, decisions, and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyTitle

-0.55

χος

-0.55

FormTagHelper

-0.52

HasForeignKey

-0.50

lowe

-0.49

ForeignKey

-0.48

援

-0.48

uno

-0.47

izade

-0.47

 scio

-0.46

POSITIVE LOGITS

 what

0.94

what

0.84

 What

0.83

AndEndTag

0.83

 WHAT

0.82

hva

0.81

What

0.80

Cosa

0.77

Čo

0.76

InvalidProtocol

0.75

Activations Density 0.123%

questions and inquiries about actions, decisions, and opinions

No Comments

No Known Activations