INDEX

Explanations

terms related to identification and verification processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.85

NOPQRST

-0.74

 beginnetje

-0.66

blij

-0.64

җ

-0.64

 سكانية

-0.63

出版年

-0.63

mäh

-0.62

 sicura

-0.62

enderror

-0.60

POSITIVE LOGITS

tvguidetime

0.79

Tit

0.65

 unknownFields

0.62

sign

0.57

yargs

0.56

ⓧ

0.55

().__

0.55

://$

0.50

 sitten

0.50

si

0.49

Activations Density 0.076%

terms related to identification and verification processes

No Comments

No Known Activations