INDEX

Explanations

terms and phrases related to entities in data structures or APIs

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

 Koen

-0.96

 Fros

-0.92

JAS

-0.89

<<-

-0.88

 Epif

-0.88

CEA

-0.82

évaluateur

-0.82

 Shakspeare

-0.82

isSuccessful

-0.82

 isShow

-0.82

POSITIVE LOGITS

 entity

1.74

 Entities

1.69

entity

1.66

entities

1.65

 entities

1.63

ENTITY

1.63

 Entity

1.60

 ENTITY

1.55

Entities

1.51

Entity

1.37

Activations Density 0.009%

terms and phrases related to entities in data structures or APIs

No Comments

No Known Activations