INDEX

Explanations

negative associations or sentiments related to individuals or entities

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

 trompe

-0.51

tentu

-0.50

 touch

-0.50

 time

-0.49

of

-0.48

 duong

-0.47

在下

-0.46

set

-0.46

 text

-0.45

రం

-0.45

POSITIVE LOGITS

Personensuche

1.04

typeorm

0.86

expandindo

0.84



0.78

OGND

0.77

CppMethod

0.75

timewa

0.72

RTEE

0.70

tvguidetime

0.69

 Мексичка

0.68

Activations Density 0.430%

negative associations or sentiments related to individuals or entities

No Comments

No Known Activations