INDEX

Explanations

transformative actions or processes

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

-1.03

ThroughAttribute

-0.94

 myſelf

-0.90

providedIn

-0.89

 propOrder

-0.88

脚注の使い方

-0.86

Personensuche

-0.85

sizeCache

-0.83

 InputDecoration

-0.83

GEBURTSDATUM

-0.82

POSITIVE LOGITS

 become

0.89

0.88

 became

0.83

Become

0.78

 turned

0.78

 Become

0.77

变成

0.77

 becomes

0.77

 transformed

0.77

 transforma

0.76

Activations Density 0.179%

transformative actions or processes

No Comments

No Known Activations