INDEX

Explanations

specific references or markers indicating the beginning of a new section or important statement in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

dem

-0.56

two

-0.54

Dem

-0.53

 Numerade

-0.53

-0.52

แป

-0.51

キシ

-0.49

Kur

-0.47

dem

-0.46

Ly

-0.46

POSITIVE LOGITS

BufferException

0.86

 Roskov

0.82

 smtplib

0.81

دانشنامهٔ

0.80

fromnode

0.80

 ddelweddau

0.79

########.

0.75

цездатний

0.74

IntoConstraints

0.74

 otomatig

0.71

Activations Density 0.244%

specific references or markers indicating the beginning of a new section or important statement in text

No Comments

No Known Activations