INDEX

Explanations

expressions of opinion and personal beliefs

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

rxjs

-0.83

IntoConstraints

-0.81

writeFieldEnd

-0.80

 للمعارف

-0.78

CloseOperation

-0.73

 виправивши

-0.72

 Normdatei

-0.69

 שוליים

-0.69

">//

-0.68

 '\\;'

-0.68

POSITIVE LOGITS

 understand

3.03

 understanding

2.92

 understood

2.82

 understands

2.70

understand

2.67

 Understand

2.63

 Understanding

2.58

understanding

2.57

Understand

2.52

Understanding

2.45

Activations Density 0.354%

expressions of opinion and personal beliefs

No Comments

No Known Activations