INDEX

Explanations

references to specific entities or names related to "Nor"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ainfi

-1.04

 iſt

-0.99

 itſelf

-0.95

 Monfieur

-0.94

 auffi

-0.93

 متعلقه

-0.92

ſy

-0.90

 myſelf

-0.89

 purpoſe

-0.89

 ſche

-0.88

POSITIVE LOGITS

 Prom

0.75

де

0.74

hot

0.69

Nor

0.68

hot

0.67

 promise

0.67

prom

0.66

gonic

0.65

Hot

0.65

 talk

0.64

Activations Density 0.089%

references to specific entities or names related to "Nor"

No Comments

No Known Activations