INDEX

Explanations

responses and statements involving answers or explanations to questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

RepeatedField

-0.65

 caufe

-0.63

はじめに

-0.63

 estekak

-0.61

 cauſe

-0.60

notations

-0.59

 sanguí

-0.59

igate

-0.58

glLoad

-0.58

 dysplasia

-0.57

POSITIVE LOGITS

 answers

1.07

 Answers

1.02

 questions

0.97

ANSWER

0.94

answers

0.93

Answers

0.93

 Answer

0.87

 answer

0.84

 ANSWERS

0.77

answer

0.76

Activations Density 0.048%

responses and statements involving answers or explanations to questions

No Comments

No Known Activations