INDEX

Explanations

first-person and second-person pronouns, emphasizing personal and direct engagement

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

TagMode

-0.55

 चीज़ों

-0.47

μων

-0.45

кової

-0.42

vrigt

-0.42

 нём

-0.41

 quelles

-0.41

 CURLOPT

-0.41

andidat

-0.41

 produrre

-0.41

POSITIVE LOGITS

ⓧ

0.75

 Ause

0.68

cshtml

0.65

uminense

0.65

 Wikimedijinoj

0.62

hematics

0.62

ʖ

0.62

 poveznice

0.60

khu

0.59

Comté

0.59

Activations Density 0.520%

first-person and second-person pronouns, emphasizing personal and direct engagement

No Comments

No Known Activations

first-person and second-person pronouns, emphasizing personal and direct engagement

No Comments

No Known Activations