INDEX

Explanations

references to questions, particularly their phrasing and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Personendaten

-0.84

lepiej

-0.79

 mijne

-0.77

 paroisse

-0.77

edn

-0.77

godic

-0.76

felves

-0.76

]-'

-0.75

 gloire

-0.74

بوابة

-0.74

POSITIVE LOGITS

 question

2.23

 questions

2.22

 Question

2.12

question

2.00

 Questions

1.91

Question

1.90

 QUESTION

1.86

questions

1.83

Questions

1.83

QUESTION

1.66

Activations Density 0.054%

references to questions, particularly their phrasing and structure

No Comments

No Known Activations