INDEX

Explanations

phrases expressing degrees of comparison and evaluations regarding various subjects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 very

-0.87

 extremely

-0.82

 utterly

-0.73

 exceedingly

-0.73

 entirely

-0.72

extremely

-0.71

 absolutely

-0.71

very

-0.70

 incredibly

-0.69

 totally

-0.68

POSITIVE LOGITS

########.

0.77

ChromeDriver

0.61

writeFieldEnd

0.57

OrNil

0.55

RegressionTest

0.54

#+#

0.53

!*\

0.50

Демографія

0.50

SourceChecksum

0.50

multer

0.49

Activations Density 0.123%

phrases expressing degrees of comparison and evaluations regarding various subjects

No Comments

No Known Activations