INDEX

Explanations

negation or denial phrases 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 bezeichneter

-0.72

Spoljašnje

-0.70

 ModelExpression

-0.61

 Hadrian

-0.59

 كومونز

-0.58

squareup

-0.57

 kuan

-0.56

XK

-0.56

 sibi

-0.56

 lenker

-0.56

POSITIVE LOGITS

in

1.31

 في

1.19

In

1.13

Dalam

1.11

InThe

1.09

 ใน

1.09

 در

1.08

 trong

1.08

в

1.07

IN

1.06

Activations Density 0.037%

negation or denial phrases in the text

No Comments

No Known Activations