INDEX

Explanations

nouns or pronouns related to entities or subjects in a document

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

astify

-0.72

 mør

-0.65

 umana

-0.63

 missione

-0.62

 honte

-0.62

 leçons

-0.61

 cápsulas

-0.60

 pitié

-0.60

 leçon

-0.59

 négociations

-0.59

POSITIVE LOGITS

檚

0.89

0.68

0.67

")]

0.66

<bos>

0.64

")));

0.64

ее

0.64

ontes

0.59

ôs

0.58

not

0.58

Activations Density 0.166%

nouns or pronouns related to entities or subjects in a document

No Comments

No Known Activations