INDEX

Explanations

notions of negation or contrast in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.62

-0.56

-0.54

-0.49

<strong>

-0.48

-0.44

and

-0.44

amp

-0.43

POSITIVE LOGITS

 itſelf

1.20

aarrggbb

1.19

 myſelf

1.06

 Theſe

1.06

 faſt

1.04

 autorytatywna

1.03

 Reſ

1.01

 consultato

1.00

 Monfieur

0.98

 raiſ

0.97

Activations Density 0.294%

notions of negation or contrast in various contexts

No Comments

No Known Activations