INDEX

Explanations

terms associated with judgment and evaluation

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

 verkle

-0.71

----------------

-0.69

 commis

-0.69

いい

-0.69

 apocalypse

-0.68

Richards

-0.66

わた

-0.66

XXXXXXXX

-0.66

 Hartmann

-0.66

POSITIVE LOGITS

 useStyles

0.94

 jugé

0.86

MessageTagHelper

0.84

resizingMask

0.82

 âgées

0.81

LookAnd

0.81

 WaitForSeconds

0.79

 juger

0.78

useNewUrlParser

0.77

RenderAtEndOf

0.77

Activations Density 0.249%

terms associated with judgment and evaluation

No Comments

No Known Activations