INDEX

Explanations

text that describes attributes or characteristics of items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 myſelf

-1.12

 themſelves

-0.97

 himſelf

-0.90

 becauſe

-0.87

 Monfieur

-0.86

 perſon

-0.86

 Jefus

-0.86

ſelf

-0.86

Efq

-0.85

 cauſe

-0.83

POSITIVE LOGITS

0.83

 features

0.80

an

0.73

unyai

0.65

 lots

0.64

the

0.61

 contain

0.61

Features

0.60

 Features

0.60

 distinct

0.59

Activations Density 0.463%

text that describes attributes or characteristics of items or concepts

No Comments

No Known Activations

text that describes attributes or characteristics of items or concepts

No Comments

No Known Activations