INDEX

Explanations

phrases indicating evidence or findings related to subjects being discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 ujednoznacz

-0.96

NameInMap

-0.91

 esetén

-0.79

 дописавши

-0.70

antMatchers

-0.56

GEBURTSDATUM

-0.56

 ModelExpression

-0.55

exitRule

-0.55

 &___

-0.55

 beginnetje

-0.54

POSITIVE LOGITS

 itself

0.81

 themselves

0.63

itself

0.61

 بيها

0.60

 Itself

0.58

 مرح

0.55

thmus

0.54

reactstrap

0.54

[++

0.54

vinas

0.51

Activations Density 1.870%

phrases indicating evidence or findings related to subjects being discussed

No Comments

No Known Activations