INDEX

Explanations

mentions of telephone-related terms and conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 jugé

-0.73

 trail

-0.72

thru

-0.70

 πως

-0.70

kids

-0.69

 Gentry

-0.68

trail

-0.68

 meds

-0.68

ajur

-0.67

 Furman

-0.67

POSITIVE LOGITS

cination

0.99

ogeneous

0.97

parsedMessage

0.94

 Telephone

0.90

TTTT

0.88

StateException

0.87

andum

0.87

 nahilalakip

0.87

ISTICS

0.87

Advertisements

0.86

Activations Density 0.907%

mentions of telephone-related terms and conversations

No Comments

No Known Activations