INDEX

Explanations

forward-looking statements indicating potential risks and uncertainties in company communications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

PerformLayout

-1.04

Vidite

-1.01

RenderAtEndOf

-1.01

 nakalista

-0.96

 autorytatywna

-0.93

 للمعارف

-0.93

ConstraintMaker

-0.91

 resourceCulture

-0.89

存于互联网档案馆

-0.88

expandindo

-0.87

POSITIVE LOGITS

men

0.42

Memorials

0.42

 erinner

0.41

 most

0.41

einander

0.40

enging

0.40

족

0.40

 Дру

0.40

postMessage

0.39

Activations Density 0.034%

forward-looking statements indicating potential risks and uncertainties in company communications

No Comments

No Known Activations