INDEX

Explanations

occurrences of the word "question" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

lepiej

-0.86

utuhkan

-0.85

godic

-0.78

(;;)

-0.76

^(@)

-0.75

 paroisse

-0.73

abbé

-0.73

edn

-0.73

 terbukti

-0.73

curate

-0.72

POSITIVE LOGITS

 questions

1.93

 question

1.74

 Question

1.71

 Questions

1.69

Questions

1.59

questions

1.56

question

1.54

 QUESTION

1.48

Question

1.47

 QUESTIONS

1.35

Activations Density 0.054%

occurrences of the word "question" and its variations in different contexts

No Comments

No Known Activations