INDEX

Explanations

references or phrases signaling importance or relevance in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 похо

-0.48

iseaux

-0.47

 maxn

-0.44

似

-0.42

Expedia

-0.42

<bos>

-0.41

InputTagHelper

-0.41

 firebaseConfig

-0.41

 useAuth

-0.40

lež

-0.40

POSITIVE LOGITS

IsMutable

0.76

 This

0.72

----</

0.70

writeFieldEnd

0.70

 للمعارف

0.69

 These

0.69

 nahilalakip

0.68

 protoimpl

0.68

 Detta

0.67

elance

0.66

Activations Density 0.340%

references or phrases signaling importance or relevance in the text

No Comments

No Known Activations