INDEX

Explanations

positive and negative sentiment indicators in a 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.96



-0.91

 оригіналу

-0.90

 Walkover

-0.89

 cire

-0.87

 Malk

-0.87

InjectAttribute

-0.85

 Monfieur

-0.83

crumb

-0.83

 Cire

-0.82

POSITIVE LOGITS

Pos

2.19

pos

2.18

pos

2.17

Pos

2.03

POS

1.83

POS

1.79

 POSS

1.27

 poses

1.24

getPos

1.24

Poss

1.21

Activations Density 0.075%

positive and negative sentiment indicators in a text

No Comments

No Known Activations