INDEX

Explanations

nouns related to relationships and their 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

 McGu

-0.49

 Cientí

-0.48

newData

-0.46

Bav

-0.46

Cannot

-0.45

 пя

-0.45

 myst

-0.45

Kom

-0.45

ódz

-0.45

IFORN

-0.44

POSITIVE LOGITS

 relation

1.13

relation

1.11

Relation

1.10

 Relation

1.09

 relations

1.09

 Relations

1.02

relations

1.00

 RELATION

0.98

 RELATIONS

0.92

Relations

0.88

Activations Density 0.008%

nouns related to relationships and their dynamics

No Comments

No Known Activations