INDEX

Explanations

references to the concept of "facts" or factual accuracy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 nahilalakip

-0.98

verwijspagina

-0.78

 становника

-0.76

 esternos

-0.76

indd

-0.74

`,

-0.69

webElementXpaths

-0.69

")));

-0.68

.")

-0.68

POSITIVE LOGITS

 facts

1.38

 acknowledge

1.26

 Facts

1.19

facts

1.11

 Acknowled

1.10

ack

1.09

 Acknowledge

1.08

 acknowledges

1.08

 factual

1.08

 acknowledged

1.07

Activations Density 0.072%

references to the concept of "facts" or factual accuracy

No Comments

No Known Activations