INDEX

Explanations

references to notable figures or leaders in specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 дописавши

-0.98

 bezeichneter

-0.93

 tartalomajánló

-0.92

findpost

-0.88

 purpoſe

-0.88

PerformLayout

-0.86

WithIOException

-0.86

 greateſt

-0.84

 reaſon

-0.84

rrggbb

-0.82

POSITIVE LOGITS

and

0.45

‐

0.43

0.42

to

0.40

but

0.39

 farm

0.39

ditto

0.39

лку

0.38

 SqlParameter

0.38

in

0.38

Activations Density 0.678%

references to notable figures or leaders in specific contexts

No Comments

No Known Activations