INDEX

Explanations

phrases indicating conditions or causal relationships

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

GHIJKLM

-0.86

GGGG

-0.84

VES

-0.79

verwijspagina

-0.77

VOS

-0.76

reciated

-0.75

GOS

-0.73

 Rhymes

-0.71

</tfoot>

-0.71

諗

-0.71

POSITIVE LOGITS

that

1.73

 that

1.52

THAT

1.52

 That

1.50

That

1.49

 THAT

1.45

 bahwa

0.97

migrationBuilder

0.96

 bahawa

0.91

Thats

0.91

Activations Density 3.804%

phrases indicating conditions or causal relationships

No Comments

No Known Activations