INDEX

Explanations

phrases and keywords related to requests for help or advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 purpoſe

-0.86

 enfans

-0.82

 Monfieur

-0.79

 ainfi

-0.77

 auffi

-0.76

 feroit

-0.75

 avoient

-0.74

 ſtate

-0.74

 déput

-0.74

 ſta

-0.73

POSITIVE LOGITS

 onCancelled

0.64

 pinulongan

0.61

Източници

0.54

Біографія

0.54

 الاطلاع

0.54

InstrumentedTest

0.53

bootstrapcdn

0.53

ниці

0.53

ExtendWith

0.52

ниця

0.52

Activations Density 0.006%

phrases and keywords related to requests for help or advice

No Comments

No Known Activations