INDEX

Explanations

terms related to faults, attributes, and characteristics of items or concepts, particularly identifying negative aspects or "culprits."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.67

 CommonModule

-0.65

PyErr

-0.65

Efq

-0.64

jalá

-0.63

 Curs

-0.62

 ་་

-0.60

 theſe

-0.60

 uſe

-0.60

LLocation

-0.60

POSITIVE LOGITS

 itself

0.72

itself

0.56

 Itself

0.54

asker

0.52

 كورة

0.51

 culprit

0.50

凶

0.49

Sib

0.48

dia

0.47

$_

0.47

Activations Density 0.769%

terms related to faults, attributes, and characteristics of items or concepts, particularly identifying negative aspects or "culprits."

No Comments

No Known Activations