INDEX

Explanations

phrases indicating personal experiences 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 @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Мексичка

-0.66

 gyhoeddwyd

-0.64

 发表于

-0.63

 '\\;'

-0.61

WithIOException

-0.55

 كومونز

-0.55

urlpatterns

-0.54

 Polsek

-0.53

apture

-0.52

 चीज़ों

-0.52

POSITIVE LOGITS

 research

2.15

 researching

2.04

 researched

1.98

research

1.90

 googling

1.82

Research

1.79

 Research

1.79

 google

1.78

 Google

1.72

 RESEARCH

1.71

Activations Density 0.527%

phrases indicating personal experiences and opinions

No Comments

No Known Activations