INDEX

Explanations

ratings related to approval and disapproval, particularly in the context of polling data

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

 deleteById

-0.55

iexcl

-0.48

 impacted

-0.47

 magnifying

-0.45

distan

-0.43

loco

-0.43

 ApiException

-0.42

 Resource

-0.42

ampiyon

-0.42

 Affected

-0.41

POSITIVE LOGITS

bootstrapcdn

0.73

XmlAccessType

0.68

 Audiodateien

0.65

الحياه

0.65

setVerticalGroup

0.64

 propOrder

0.64

ANTLR

0.63

omitempty

0.62

Демографія

0.61

帖最后由

0.61

Activations Density 0.047%

ratings related to approval and disapproval, particularly in the context of polling data

No Comments

No Known Activations