INDEX

Explanations

phrases indicating interpersonal relationships and emotional dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.39

Ӕ

-0.38

 productividad

-0.32

REFERRED

-0.31

 œuvre

-0.31

 võimal

-0.31

 princesse

-0.31

 nying

-0.30

 complejidad

-0.30

 bahía

-0.30

POSITIVE LOGITS

fromnode

0.68

writeFieldEnd

0.63

TypedDataSet

0.63

ⓧ

0.57

 NSCoder

0.57

sizeCache

0.56

richTextPanel

0.56

RegressionTest

0.56

󠁴

0.54

ReusableCell

0.52

Activations Density 0.138%

phrases indicating interpersonal relationships and emotional dynamics

No Comments

No Known Activations