INDEX

Explanations

terms related to susceptibility and vulnerability in infectious contexts

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

 rangers

-0.77

 Ranger

-0.75

Ranger

-0.71

httphttps

-0.68

LikeLike

-0.68

<h3>

-0.67

 ranger

-0.66

Uda

-0.65

idge

-0.64

elf

-0.63

POSITIVE LOGITS

ceptibility

1.30

 susceptibility

1.09

ceptible

1.07

 ISNI

0.82

 susceptible

0.82

 suscepti

0.82

 touristique

0.77

IActionResult

0.71

 Scully

0.69

SUCCEEDED

0.69

Activations Density 0.006%

terms related to susceptibility and vulnerability in infectious contexts

No Comments

No Known Activations

terms related to susceptibility and vulnerability in infectious contexts

No Comments

No Known Activations