INDEX

Explanations

relationships and structures related to cause-and-effect scenarios in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

uxxxx

-0.76

Välislingid

-0.70

CppMethod

-0.69

#+#

-0.69

 Roskov

-0.69

 autorytatywna

-0.69

 ModelExpression

-0.67

///</

-0.67

 CreateTagHelper

-0.66

aarrggbb

-0.64

POSITIVE LOGITS

wieś

0.61

 comunque

0.52

 anyways

0.50

 whatsoever

0.50

 anyway

0.48

 anyhow

0.47

 ändå

0.46

somewhere

0.45

といえば

0.44

 amorphous

0.44

Activations Density 0.484%

relationships and structures related to cause-and-effect scenarios in text

No Comments

No Known Activations