INDEX

Explanations

relationships between parts of a narrative or model

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

IndentedString

-0.58

 &___

-0.58

ituary

-0.54

AccessorTable

-0.53

تقاوى

-0.52

breos

-0.50

 mxArray

-0.50

SourceChecksum

-0.49

✨:

-0.49

rible

-0.48

POSITIVE LOGITS

НИК

0.56

ecuted

0.54

netinet

0.53

 تضيفلها

0.52

maline

0.52

ény

0.52

 ulang

0.52

ennan

0.51

 voca

0.50

Formik

0.50

Activations Density 0.219%

relationships between parts of a narrative or model

No Comments

No Known Activations