INDEX

Explanations

negative sentiments expressed through various phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

$_['

-0.53

fromnode

-0.51

jsonwebtoken

-0.49

 cucchia

-0.49

 byen

-0.48

interopRequire

-0.48

 cucchiaio

-0.48

expiresIn

-0.46

 AspNetCore

-0.46

 legno

-0.45

POSITIVE LOGITS

我就

0.63

 Anyway

0.63

 Надо

0.59

 dunno

0.58

Kalau

0.58

怎麼

0.57

不就是

0.57

 Pakai

0.57

 Anyways

0.56

ınca

0.56

Activations Density 0.056%

negative sentiments expressed through various phrases

No Comments

No Known Activations