INDEX

Explanations

negative or contrasting terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 Roskov

-0.70

libft

-0.67

cotch

-0.63

iterranée

-0.59

ciech

-0.58

ständig

-0.56

IZONA

-0.54

 EdgeInsets

-0.54

vician

-0.54

ască

-0.54

POSITIVE LOGITS

 незавершена

0.67

TestingModule

0.67

ISupport

0.66

Parcelize

0.61

 protoimpl

0.59

WillAppear

0.59

THON

0.56



0.53

 дописавши

0.53

‐

0.52

Activations Density 0.551%

negative or contrasting terms

No Comments

No Known Activations