INDEX

Explanations

conditional phrases indicating uncertainty or stipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Архівовано

-0.65

InputBorder

-0.62

tonode

-0.53

NameInMap

-0.52

<?

-0.50

IsContent

-0.48

 bezeichneter

-0.48

ISupport

-0.48

IGraphics

-0.47

extAlignment

-0.47

POSITIVE LOGITS

 überhaupt

0.70

 Audiodateien

0.66

 nemlig

0.65

 cielos

0.64

twimg

0.63

 préc

0.59

 neutre

0.59

 épu

0.58

 dépla

0.55

UnusedPrivate

0.55

Activations Density 0.190%

conditional phrases indicating uncertainty or stipulations

No Comments

No Known Activations