INDEX

Explanations

instances of negation or disagreement in the text

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 restTemplate

-0.82

 तरह

-0.78

Koc

-0.75

XMLHttpRequest

-0.74

 Felici

-0.73

 šķ

-0.71

pon

-0.70

 RestTemplate

-0.70

lli

-0.69

mrow

-0.69

POSITIVE LOGITS

¬

1.21

parsedMessage

1.12

 propOrder

0.91

¬

0.82

0.79

afone

0.75

RegressionTest

0.72

migrationBuilder

0.69

Sut

0.68

Portale

0.68

Activations Density 0.000%

instances of negation or disagreement in the text

No Comments

No Known Activations

instances of negation or disagreement in the text

No Comments

No Known Activations