INDEX

Explanations

phrases related to product specifications and user-related instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

protoimpl

-0.71

GenerationType

-0.62

 ویکی‌پدیا

-0.61

 createContext

-0.58

Personendaten

-0.57

umbai

-0.57

TagHelper

-0.57

WEBPACK

-0.57

letoe

-0.56

InjectAttribute

-0.56

POSITIVE LOGITS

gridy

0.49

RTEX

0.47

 IFTT

0.47

OGND

0.45

InvalidProtocol

0.45

setof

0.44

ửa

0.42

ctypes

0.41

annte

0.41

 tele

0.40

Activations Density 0.166%

phrases related to product specifications and user-related instructions

No Comments

No Known Activations