INDEX

Explanations

proper names and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

setVerticalGroup

-0.65

oa̍t

-0.61

 للمعارف

-0.50

 مشين

-0.50

Manbalar

-0.50

createCanvas

-0.48

✨:

-0.45

tvguidetime

-0.45

 recevez

-0.44

OrNil

-0.43

POSITIVE LOGITS

setof

0.63

 Saver

0.59

Hozzáférés

0.59

SwitchCompat

0.58

FormTagHelper

0.57

 ExecuteAsync

0.57

trung

0.55

ladin

0.55

Ute

0.54

(;;)

0.54

Activations Density 1.341%

proper names and references

No Comments

No Known Activations