INDEX

Explanations

variations of the word "question"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

WriteTagHelper

-0.75

gdx

-0.72

]-'

-0.71

dhury

-0.66

ituaries

-0.66

Personendaten

-0.66

AndEndTag

-0.65

StrictEqual

-0.65

^(@)

-0.65

værende

-0.64

POSITIVE LOGITS

 questions

1.01

 answered

0.96

 posed

0.88

 Questions

0.87

questions

0.85

Questions

0.83

 Question

0.78

Answered

0.76

 unanswered

0.76

 answers

0.75

Activations Density 0.093%

variations of the word "question"

No Comments

No Known Activations