INDEX

Explanations

non-informative tokens and formatting characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

createFrom

-0.48

broek

-0.45

goc

-0.45

atik

-0.45

جل

-0.45

 Brother

-0.45

liste

-0.44

 terciopelo

-0.44

向

-0.44

 Baumann

-0.43

POSITIVE LOGITS

AddTagHelper

0.98

InjectAttribute

0.91

ArrowToggle

0.87

sizeCache

0.85

DockStyle

0.84

 autorytatywna

0.81

OGND

0.77

DeleteBehavior

0.75

 MenuView

0.75

HostException

0.75

Activations Density 0.701%

non-informative tokens and formatting characters in the text

No Comments

No Known Activations