INDEX

Explanations

phrases related to quantities or conditions that indicate lower amounts or reduced presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 المعيارى

-0.56

VIAF

-0.55

inaldi

-0.53

AnimationsModule

-0.52

 Aitken

-0.51

RectangleBorder

-0.50

otide

-0.50

Gön

-0.49

Portale

-0.49

 Marino

-0.48

POSITIVE LOGITS

ess

0.79

esse

0.76

Ess

0.68

less

0.66

ss

0.66

cess

0.66

Ess

0.65

esses

0.65

esser

0.65

esch

0.65

Activations Density 0.150%

phrases related to quantities or conditions that indicate lower amounts or reduced presence

No Comments

No Known Activations