INDEX

Explanations

words and phrases related to personal identification and legal terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

PerformLayout

-0.76

-0.75

ttemberg

-0.65

-0.61

-0.59

ficulty

-0.57

ViewFeatures

-0.57

retum

-0.56

the

-0.56

POSITIVE LOGITS

Efq

1.03

ⓧ

0.94

 xenia

0.94

 Majefty

0.90

 depositphotos

0.89

 pngtree

0.88

 NDEBUG

0.88

 myſelf

0.87

μως

0.87

 ſever

0.86

Activations Density 4.738%

words and phrases related to personal identification and legal terms

No Comments

No Known Activations