INDEX

Explanations

boolean values that indicate "true" conditions or states

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

 comp

-0.72

 jScrollPane

-0.68

เภ

-0.67

 تانيه

-0.66

}{*}{

-0.66

cessed

-0.65

 المعيارى

-0.63

pherd

-0.63

XmlAccessType

-0.61

degard

-0.61

POSITIVE LOGITS

False

1.06

True

0.97

 True

0.92

 False

0.91

Ei

0.73

 django

0.71

Kingdom

0.69

django

0.67

pulumi

0.67

TTS

0.66

Activations Density 0.059%

boolean values that indicate "true" conditions or states

No Comments

No Known Activations