INDEX

Explanations

terms related to modifiers in a sentence

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

 Nelson

-0.57

})`

-0.56

amarine

-0.54

mazioni

-0.54

 없습니다

-0.53

its

-0.52

-0.51

ara

-0.51

POSITIVE LOGITS

 modifier

1.45

 Modifier

1.44

 modifiers

1.38

Modifier

1.29

modifiers

1.26

Modifiers

1.22

modifier

1.14

 Diſ

1.05

AddTagHelper

1.01

jooq

1.00

Activations Density 0.001%

terms related to modifiers in a sentence

No Comments

No Known Activations